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/starter-series/create-starter/proof-reportgit clone --depth 1 https://github.com/starter-series/create-starterWhat 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 | $0.00020 | $0.00328 |
| Opus 5 | $0.00010 | $0.00164 |
| Sonnet 5 | $0.00004 | $0.00066 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
proof-report 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.
What it actually says
You are generating a Launch Proof Report for an existing repo.
Steps
-
Call the
generate_launch_proof_reportMCP tool with:path: the absolute path of the repo to check. If no path is given, use the MCP server's cwd.write:trueonly when the user wantslaunch-proof-report.mdwritten to disk; otherwise leave it false and return the Markdown.output_path: optional. Use only when the user asked for a specific file path.
-
Surface the structured verdict first:
- overall —
ready,attention, orblocked - gates — release, CD, security
- blockers — fixes required before launch
- warnings — human-review items
- overall —
-
If the report is not
ready, propose the next command:- release issue ->
/audit-release - publish drift ->
/audit-cd - security posture ->
/audit-security - missing CI/CD files ->
/add-component
- release issue ->
-
If the user is packaging this as a client handoff, recommend writing the report and committing it with the exact audited commit SHA noted in the surrounding message.
Do NOT
- Call the result "certified" or imply legal/store/security certification.
- Modify app code.
- Trigger publish, tag, deploy, or release workflows.
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 · 34 lines · 20 tokens per session scan A d3f92fbee610
proof-report is a command published in the GitHub repository starter-series/create-starter (1 stars, last pushed 14d ago), licensed MIT. It adds 20 tokens to every session and 328 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
local-ci-dev
Run local CI to verify changes before completing work.
domains
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
access
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
test-integration
Write integration tests for component boundaries.
analyst
Use when performing local analyst review before pushing PR changes. Assesses code quality, impact analysis, and maintainability.
newpkg
Generate new package with Nx.