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.
git clone --depth 1 https://github.com/gosha70/code-copilot-teamWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/gosha70/code-copilot-team/shape)<a href="https://agentmods.dev/commands/gosha70/code-copilot-team/shape"><img src="https://agentmods.dev/badge/commands/gosha70/code-copilot-team/shape/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/gosha70/code-copilot-team/shape"><img src="https://agentmods.dev/badge/commands/gosha70/code-copilot-team/shape.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00000 | $0.00379 |
| Opus 5.5 | $0.00000 | $0.00152 |
| Sonnet 5.5 | $0.00000 | $0.00076 |
| Haiku 4.5 | $0.00000 | $0.00038 |
Grade A, and why
shape 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 1mo 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
Shape a rough idea into a Shape-Up pitch via the pitch-shaper agent.
Usage: /shape <topic>
Steps
1. Parse arguments
The <topic> is the rough idea — a one-line description (e.g. add streaming responses to the chat API). If absent, ask the user for one.
2. Invoke pitch-shaper
Use the Agent tool with subagent_type: pitch-shaper. Pass the topic and any additional context the user has volunteered.
The pitch-shaper will:
- Pick the next
NNNN-slugpitch id underspecs/pitches/ - Ask clarifying questions (appetite, problem, solution shape, no-gos, circuit breaker)
- Decompose into 3–7 scopes
- Write
specs/pitches/<id>/pitch.mdfrom~/.claude/templates/sdd/pitch-template.md - Set
bet_status: shaped - Validate via
~/.claude/templates/sdd/validate-pitch.sh
3. Report to user
Once pitch-shaper returns, print:
- The new pitch path
- Frontmatter summary (id, appetite, scope count, circuit breaker)
- Validator confirmation
- Next step: "Run
/bet <pitch-id>to lock this as a bet for the next cycle, or refine via direct edits."
Notes
- This command does not lock the pitch as a bet.
bet_status: shapedmeans "ready for the betting table" — not yet committed. - A pitch can sit in
shapedindefinitely. Only/betadvances tobet_status: bet. - Re-running
/shapefor the same topic produces a NEW pitch with a new id — it does not overwrite. Edit the existing pitch directly if you want to refine.
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.
- 1mo ago First seen · 36 lines · 0 tokens per session scan A a6167d6bc2da
shape is a command published in the GitHub repository gosha70/code-copilot-team (7 stars, last pushed 17d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 379 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
story-continue
Resume an interrupted story from where you left off.
rosetta-grill
Grill the user about a plan or design — but grounded in Rosetta's resolved decision state — then RECORD the outcome as an ADR/PDR. Use when the user wants to stress-test a decision, says "grill me on this", or wants a decision interrogated and captured. Integrates grill-me-style interrogation with Rosetta's…
rosetta-preflight
Produce Rosetta's deterministic preflight JSON for a scoped change: optional RA1 structural report, decision-state resolution, and local Rosetta gates. Use before handing execution to a loop runner.
check-drift
Run schema drift detection — compare the live Postgres schema against ORM table definitions, backend function .select() calls, the schema doc, and the techstack inventory.
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.