the idea the single source of truth one plan per person branches, context, and a generated rules file every session starts the same way two audits, one table, one fix pass never skip the checkpoint a fresh eye on everything committed

plan it before you build it.

an interactive walkthrough of a prompt-driven workflow for AI-assisted hackathon development. eight phases, each with a prompt you can copy and an exit condition you can check. built for small teams who want the discipline of a big one without the overhead.

8 phases
9 copyable prompts
3 guardrail skills

front-load every decision, then let the agent execute.

most teams start a hackathon by opening an editor and hoping for the best. this workflow does the opposite. every decision, constraint, and plan goes into structured documents before a single line of code is written. the coding agent then executes against those documents, phase by phase, and a human reviews every transition point.

the result: less debugging, fewer merge conflicts, no "wait, what are we building again" at 3am.

the whole thing runs like a loop: plan, code, test, review, repeat. each phase has a prompt to use and an exit condition to check. nothing depends on memory or improvisation. a phase is done when its checkboxes are ticked, not when it roughly feels done.

six tools and three skills.

tools

  • claude for ideation and plan generation.
  • opencode your local agent that reads your directory and writes code.
  • mimo code an opencode clone with mimo models.
  • freebuff a coding agent with 6-hour free sessions daily.
  • git one branch per member, nobody pushes to main directly.
  • terax (or another terminal emulator) worth using in place of powershell.

guardrail skills

install these globally once. the same skills work in whichever agent you land on.

skillwhen
ponytail · forces minimal, non-overengineered code every phase
hallmark · anti-slop UI, picks structure and theme before building frontend build
impeccable · 59-rule UI audit frontend audit
install
npx skills add DietrichGebert/ponytail
npx skills add nutlope/hallmark
npx impeccable install

copy the templates, fill them in, return them.

the repo ships with template files you copy into each project, fill in, and return from:

context/
context/
├── readme.md
├── idea.md
├── spec.md
├── plan.md
├── phase-review.md
└── postmortem.md

at the start of a project, copy these into your repo and fill them out. the originals stay untouched. after a project, update the originals based on what you learned. that return loop is what makes the system get smarter.

eight phases. copy the prompt, check the exit, move on.

the whole flow, from idea to post-mortem. each phase names its tool, its file, the prompt to hand your agent, and the exit condition that says you're done.

ideaspecplanrepobuildauditreviewshippostmortemnext

phase 0 · ideation

the idea

tool claude · file idea.md

upload your hackathon or project documentation and a filled idea.md, and have claude generate eight candidate ideas before you commit to one.

prompt · claude
Here is the official hackathon document [attached file] and my project context:

[paste filled idea.md]

Generate 8 ideas. For each idea:
- One-line concept
- Core problem it solves
- Who the user is
- The single most impressive thing a judge would see in the demo
- Realistic scope for [X] hours with [Y] team
- Biggest technical risk

After the list, recommend the top 2 based on my judging criteria and team strengths.

pick one idea and sharpen it. one-sentence pitch, what the demo moment looks like, and what gets cut if time runs out. record these decisions in section 6 of idea.md as you make them.

exit condition every checkbox in the idea.md ready check is ticked. all must be yes before moving.

phase 1 · specification

the single source of truth

tool claude · file spec.md

turn the sharpened idea into a complete spec. this file is the contract every line of code traces back to, so be ruthless about scope.

prompt · claude
Here is the spec template.
Based on everything we've discussed about this project — the idea, the users, the constraints, and the tech choices — fill this out completely and in detail. Remove any [CONDITIONAL] sections that don't apply to this project type. Never leave a field blank; if something is genuinely not applicable, write "N/A" with a one-line reason.
For the architecture, data flow, and acceptance criteria sections, be especially thorough — these are what the coding agent relies on most. Be ruthless about scope: if we didn't discuss it, it goes in Out of Scope, not in Must-Have.
This file is the single source of truth. Everything the coding agent builds will trace back to it.

exit condition every must-have feature has a testable ears-format acceptance criterion: when [trigger] the system shall [behave].

phase 2 · planning

one plan per person

tool claude · file plan.md (one per member)

have claude divide the project across the team, then generate a full plan per member. every acceptance criterion must be testable without waiting on someone else's work.

prompt · claude
Here is spec.md: [attach]
Here is plan.md template: [attach]

Generate plan.md for [role].

Use the uploaded plan.md template structure as template. Pick only the phases for their scope.
Each phase must list tasks specific to their role. Acceptance criteria must be
independently testable, no other member's work required first.

exit condition every member has a plan, and every acceptance criterion maps to a feature in spec.md.

phase 3 · repository setup

branches, context, and a generated rules file

tool git + opencode

  1. create the repo.
  2. create a branch per member. nobody pushes to main directly; the one exception is shared foundation work.
  3. create the context folder in the repo root:
context/
context/
├── spec.md
└── plan-[name].md    ← one per member
  1. run opencode's /init to auto-generate AGENTS.md by analyzing the directory. don't write it by hand. it then applies your summarized habits in every session.
  2. build shared foundation work (data models, folder structure, environment setup) on main before people branch off.

exit condition repo, branches, context folder, and root AGENTS.md exist; the shared foundation runs.

phase 4 · coding

every session starts the same way

tool opencode · files context folder

open the session by forcing the agent to read the context and confirm the plan before it writes a line of code.

session start prompt
Read these files before doing anything:
- context/spec.md
- context/plan.md

Skills active this session: ponytail [+ hallmark or impeccable by phase — see table]

Do not write any code yet. Confirm you have read them by summarizing:
1. What this project does
2. What your role is responsible for
3. What phase we are currently on
4. What the acceptance criteria are for this phase
phase typeskills to load
backend, logic, apiponytail
new ui from scratchponytail, hallmark
ui audit and iterationponytail, impeccable

then run the phase in plan mode (press tab in opencode to switch plan ↔ build). replace n with whatever phase you're working on based on your plan.md file.

phase start prompt
Implement Phase [N]: [Phase Name] from my plan.

Rules:
- Finish every task in this phase before touching a future phase
- After every file you create or modify:
  1. Run the test or type check for that file
  2. Run the full suite
  3. Report both results before touching the next file
- Do not proceed if either check fails
- Do not advance to Phase [N+1] until all of Phase [N] passes
- If something falls outside the spec or plan, stop and ask. Don't invent a fix

and if the agent loops on the same error twice or more, stop it before it burns more time.

anti-loop prompt
Stop fixing this. Don't modify any files.

Explain in plain language:
1. What the error actually is
2. Why your earlier fixes failed
3. Three ways to fix it and the trade-off of each

Then wait for my decision before touching anything.

exit condition every task in the phase is done, every test and type check passes, and nothing was built that isn't in the plan.

for sessions past 2 hours: re-read spec.md and your plan, confirm which phase and task is next, and keep going.

phase 5 · frontend audit

two audits, one table, one fix pass

tool opencode (hallmark + impeccable)

after any phase that produces UI, run both audits together, merge the findings into one table, fix everything in a single pass.

merged audit prompt
Run a Hallmark audit on the project, then run an Impeccable audit too.

Present a single merged table with:
- Issue found
- Which skill flagged it (Hallmark / Impeccable / Both)
- Recommended fix

If two skills call out the same issue, list it once as "Both".
Single-skill flags get that skill's name.

fix the "both" rows first, then judge the single-skill findings and fix everything in one pass.

exit condition all "both" rows fixed, single-skill findings judged, fixes applied in one pass.

phase 6 · phase transition review

never skip the checkpoint

tool you (human) + the agent

before every phase change, even under pressure, have the agent self-review its own work before you sign off.

transition review prompt
Before we move to Phase [N+1], review everything built in Phase [N].
Don't modify any files.

Report:
1. Tasks from the plan that are incomplete or missing
2. Hardcoded values that should be env vars
3. Unhandled error states
4. Tests that could false-pass
5. Anything built that wasn't in the plan
6. Whether every acceptance criterion in the spec is verifiably met

Is this phase genuinely done, or does something need fixing first?

exit condition the agent reports a clean pass and your manual check passes. sign off in phase-review.md; update the change log in spec.md if it changed.

phase 7 · merging and red team

a fresh eye on everything committed

tool opencode (new session)

once a plan is done, get a fresh session to red-team the branch as a senior engineer before it merges.

red-team review prompt
Read the following files completely before doing anything:
- context/spec.md
- context/plan-[name].md

Then scan the entire codebase — every file this member was responsible for.

Cross-reference what exists in the codebase against every task and acceptance
criterion in plan-[name].md. Then review as a senior engineer.

Report in this exact order:

1. COVERAGE — For every phase and task in plan-[name].md, state whether it is
   fully implemented, partially implemented, or missing entirely. Be specific
   about what is missing.

2. SPEC DRIFT — Does what was built match what spec.md required? List every
   deviation, no matter how small.

3. BUGS & ERRORS — Obvious bugs, unhandled error states, missing edge cases,
   hardcoded values that should be environment variables.

4. SECURITY — Any credentials, keys, or sensitive data exposed. Any input that
   is not validated. Any endpoint that is not protected when it should be.

5. SCOPE CREEP — Anything built that does not appear in plan-[name].md or
   spec.md. List the file and the specific addition.

6. MERGE RISK — Any file, function, or data structure likely to conflict with
   other members' branches based on PLAN-SHARED conventions and overlapping
   scope.

7. VERDICT — Is this branch ready to merge to main, or does something need
   fixing first? List every blocking issue explicitly.

Be blunt. Do not soften findings. Do not mention anything positive unless
it is directly relevant to a finding.

fix anything flagged, then merge to main. for publishing: ask your coding agent how to publish the codebase to github and how to deploy, but do the actual publish and deploy steps manually. once live, expect issues to surface even if the local code was flawless, so keep a cleanup routine: open the browser console, copy the errors, and hand them to the agent to chase every time. you can also check your deployment provider's log for errors.

exit condition every blocking issue from the red team is fixed, merged to main, and deployed.

it catches ai mistakes cheaply, before they compound.

most ai coding failures come from exactly these three causes. this workflow doesn't eliminate the mistakes; it catches them before they become hours of repair cost.

scored against the field.

evaluated against 12 industry standards and scored on 9 dimensions — 8.34 / 10 overall.

dimensionweightscoreweighted
specification as source of truth15%8.51.28
phase structure & human checkpoints15%9.01.35
context engineering13%8.51.11
verification & quality gates18%7.51.35
team coordination10%7.50.75
loop engineering8%7.50.60
system compounding8%9.00.72
frontend quality control7%9.50.67
documentation & knowledge transfer6%8.50.51
overall8.34 / 10

benchmarked against

standardtypesource
github spec kitopen-source framework, de facto sdd referencegithub.github.com/spec-kit
aws kiroenterprise agentic ide, ga 2026aws.amazon.com/kiro
bmad methodagentic delivery methodology, 49k+ starsaugmentcode.com/guides/bmad-method
mep — arXiv:2605.05400peer-reviewed paper, vibe x 2026, acm sigsoftarxiv.org/abs/2605.05400
superpowers frameworkagentic skills framework, 224.7k starsgithub.com/obra/superpowers
universal dev standards v2.3.0language-agnostic sdd standards, updated june 2026github.com/AsiaOstrich/universal-dev-standards
augment code sdd guideindustry practitioner field guideaugmentcode.com/guides/what-is-spec-driven-development
dev community sdd 2026engineering community field guidedev.to/krlz/spec-driven-development-in-2026
thebcms.com sdd guidecomprehensive tooling comparisonthebcms.com/blog/spec-driven-development
agents at work 2026 playbookpractitioner reliability guidepromptengineering.org
deloitte state of ai 2026enterprise ai governance researchcited in the augment code sdd guide
specops 2026 — issta/splashacademic workshop on specification-driven lifecycleconf.researchr.org/home/specops-2026

just you? drop the branches, keep everything else.

work in one branch and use everything else the same. one person asks claude for spec and plan, runs the agent phase by phase with testing, audits the ui, deploys, and debugs from console logs. you become the review that the whole team flow would use.

copied to clipboard