Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/jpesewang/solo-dev-workflow/setupgit clone --depth 1 https://github.com/jpeseWang/solo-dev-workflowWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.01115 |
| Opus 5 | $0.00000 | $0.00558 |
| Sonnet 5 | $0.00000 | $0.00223 |
| Haiku 4.5 | $0.00000 | $0.00112 |
Grade A, and why
setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup
Detect this project's stack and fill in the Project context block in AGENTS.md.
Run this once, right after installing. Everything else in the workflow reads the Project context
block — /test needs to know your test runner, /commit needs your lint command, /ship needs
your base branch. Left blank, every command guesses, and a guess that's wrong is worse than a
question.
Input: none. Anything you pass is treated as a hint (e.g. pnpm, vitest, deploys from develop).
Step 1 — Detect
Look at what's actually in the repo. Don't ask about anything you can read:
ls package.json pnpm-lock.yaml yarn.lock package-lock.json bun.lockb 2>/dev/null
ls pyproject.toml requirements.txt go.mod Cargo.toml Gemfile composer.json 2>/dev/null
ls nx.json turbo.json lerna.json pnpm-workspace.yaml 2>/dev/null # monorepo?
ls Makefile Dockerfile docker-compose.yml 2>/dev/null
# scripts are the source of truth for how this project is actually run
[ -f package.json ] && python3 -c "import json;print(json.load(open('package.json')).get('scripts',{}))"
# base branch, as configured rather than assumed
git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's|.*/||'
git rev-parse --abbrev-ref HEAD
# existing test files tell you the convention better than the config does
git ls-files | grep -iE '(\.test\.|\.spec\.|_test\.|/__tests__/|/tests?/)' | head -10
The lockfile decides the package manager — pnpm-lock.yaml means pnpm, not npm, regardless
of what the README says.
Step 2 — Fill in the block
Rewrite the Project context section of AGENTS.md with what you found:
Stack: TypeScript + Next.js 15, React 19
Install: pnpm install
Run / dev: pnpm dev
Test: pnpm test (vitest)
Lint/format: pnpm lint && pnpm format
Build: pnpm build
Base branch: main
Rules:
- Only write commands you verified exist — a script in
package.json, aMakefiletarget, a documented CLI. Never inventpnpm testbecause it's conventional. - If something genuinely isn't there (no linter, no tests yet), write
nonerather than a plausible-looking command.Test: none — no test setup yetis useful information; a command that errors is not. - Monorepo → prefer the affected-scope form (
nx affected -t test --base=origin/main). See docs/nx.md.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 109 lines · 0 tokens per session scan A 432986ae92cf
setup is a command published in the GitHub repository jpeseWang/solo-dev-workflow (2 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,115 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.