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 skills add spences10/my-pi --skill pi-review-gated-deliverygit clone --depth 1 https://github.com/spences10/my-piWrote 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/skills/spences10/my-pi/pi-review-gated-delivery)<a href="https://agentmods.dev/skills/spences10/my-pi/pi-review-gated-delivery"><img src="https://agentmods.dev/badge/skills/spences10/my-pi/pi-review-gated-delivery/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/skills/spences10/my-pi/pi-review-gated-delivery"><img src="https://agentmods.dev/badge/skills/spences10/my-pi/pi-review-gated-delivery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00040 | $0.00423 |
| Opus 5 | $0.00020 | $0.00211 |
| Sonnet 5 | $0.00008 | $0.00085 |
| Haiku 4.5 | $0.00004 | $0.00042 |
Grade A, and why
pi-review-gated-delivery 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 12d 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
Review-Gated Peer Delivery
Compose Team Mode, repository validation, and explicit human approval; do not claim peer process supervision.
Roles
- Keep the lead session review-only after delegation.
- Give one implementation session sole mutating ownership of one issue.
- Reserve Changeset creation and consequential approval for the user.
Delivery Loop
- Use
team session_list; verify the requested peer and repository. - Send one complete issue contract: scope, acceptance criteria, constraints, validation, no commit/Changeset, and next-task boundary.
- Require completion before reporting: no checkpoints or arbitrary slices. Permit early escalation only for a genuine blocker, contradiction, unsafe scope change, or missing authority.
- Require one final artifact with acceptance mapping, changed files, exact validation, diff summary, and remaining risks.
- Review independently without editing. Return
approveorchanges-requestedwith prioritized findings and exact evidence. - Repeat implementation and review until approved; never infer approval from tests, delivery, silence, or model output.
- After approval, let the user create the Changeset. Commit only after explicit user authorization and a clean final validation pass.
- Close the issue, confirm a clean tree, then assign only the next dependency-ordered issue.
Boundaries
- Do not start parallel mutation in a shared working tree.
- Do not treat mailbox delivery as liveness or continued execution.
- If a peer stops, report the limitation and ask the user to resume or open a session; never simulate supervision.
- Use a worktree and a separate contract if parallel mutation becomes necessary.
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.
- 12d ago First seen · 51 lines · 40 tokens per session scan A b9c0a722d5e9
pi-review-gated-delivery is a skill published in the GitHub repository spences10/my-pi (125 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 423 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
github
GitHub CLI (gh) for repository management, issues, pull requests, releases, workflows, search, gists, and API access. Use when the user asks about any GitHub operation — creating repos, forking, cloning, PR workflows, issue triage, CI/CD runs, code search, release management, or direct API calls. Keywords: github, gh…
github
Interact with GitHub using the gh CLI. Use for issues, PRs, CI runs, releases, and advanced API queries.
github-repo-management
Clone, create, fork, configure, and manage GitHub repositories. Manage remotes, secrets, releases, and workflows. Works with gh CLI or falls back to git + GitHub REST API via curl.
create-issue
Draft and submit a GitHub issue from a user idea or bug description, with bilingual body and correct labels.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
gh-credit-harvest
Harvest one community PR into a release branch with authorship and credit preserved, verified green, and a warm thank-you.