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/askwigconsulting/cohort/buildgit clone --depth 1 https://github.com/askwigconsulting/cohortWhat 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 | $0.00016 | $0.00370 |
| Opus 5 | $0.00008 | $0.00185 |
| Sonnet 5 | $0.00003 | $0.00074 |
| Haiku 4.5 | $0.00002 | $0.00037 |
Grade A, and why
build 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 2d ago.
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.
What it actually says
Invoke the agent-skills:incremental-implementation skill alongside agent-skills:test-driven-development.
Pick the next pending task from the plan. For each task:
- Read the task's acceptance criteria
- Load relevant context (existing code, patterns, types)
- Write a failing test for the expected behavior (RED)
- Implement the minimum code to pass the test (GREEN)
- Run the full test suite to check for regressions
- Run the build to verify compilation
- Commit with a descriptive message
- Mark the task complete and move to the next one
If any step fails, follow the agent-skills:debugging-and-error-recovery skill.
Worktrees for concurrent writes (in orchestrated work)
When /build is run as a worker task within /crew and multiple writers
run in parallel:
- Use the worktree provided by the coordinator. The coordinator creates a
per-task worktree and detached HEAD so your commits don't collide with other
workers'
.git/index.lock. - Never commit to the coordinator's shared checkout. All work happens in your worktree; commits land on the detached HEAD.
- Build and test against your worktree's scope. The coordinator runs the full suite after integrating your task serially; your job is to verify your task's acceptance criteria within the worktree.
If you are the only writer (sequential tasks, or a single /build invocation),
worktrees are optional; commit to the shared branch as usual.
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.
- 2d ago First seen · 42 lines · 16 tokens per session scan A 8886ddc0ca77
build is a command published in the GitHub repository askwigconsulting/cohort (2 stars, last pushed 25d ago), licensed MIT. It adds 16 tokens to every session and 370 once invoked, about $0.0001 per session on Opus 5. 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
tdd-task
Execute a Task using a TDD loop; record decisions/progress on the issue; open a PR that closes the Task.
develop-full
Full development workflow -- TDD, lint, test, self-review, commit organization. Provide a ticket ID or task description.
conductor-implement
Execute tasks from track plan with TDD workflow and git commits.
implement
Execute all implementation tasks from tasks.md with test-driven development, parallel batching, and atomic commits.
build
Build incrementally. Implement changes in thin vertical slices with TDD and atomic commits. Run after /plan.
build
Implement the next task incrementally — build, test, verify, commit.