pi-review-gated-delivery

pi-review-gated-delivery is a skill for Claude Code, Codex from spences10/my-pi. It costs 40 tokens per session (423 once invoked), scanned A, original, MIT.

A controlled workflow for delivering individual GitHub issues through one implementation peer and one review-only lead. GitHub issues are tracked work items, and a Changeset records package release information.

In plain words
What is it for?
Use it to delegate an issue, collect a final implementation report, review the changes, request fixes, and approve delivery before the user creates a Changeset.
Why use it?
It keeps implementation, review, approval, and release preparation separate so code is not treated as approved merely because tests pass.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to delegate an issue, collect a final implementation report, review the changes, request fixes, and approve delivery before the user creates a Changeset.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/spences10/my-pi/pi-review-gated-delivery
Install

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.

Any agent
npx skills add spences10/my-pi --skill pi-review-gated-delivery
Clone the repo
git clone --depth 1 https://github.com/spences10/my-pi

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for pi-review-gated-delivery

README.md
[![agentmods](https://agentmods.dev/badge/skills/spences10/my-pi/pi-review-gated-delivery/github.svg)](https://agentmods.dev/skills/spences10/my-pi/pi-review-gated-delivery)
Your own site
<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.

agentmods 80×15 button for pi-review-gated-delivery

Your own site · 80×15
<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>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 423 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 12d ago against content hash b9c0a722d5e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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.

.agents/pi-review-gated-delivery/SKILL.md · 51 lines

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

  1. Use team session_list; verify the requested peer and repository.
  2. Send one complete issue contract: scope, acceptance criteria, constraints, validation, no commit/Changeset, and next-task boundary.
  3. Require completion before reporting: no checkpoints or arbitrary slices. Permit early escalation only for a genuine blocker, contradiction, unsafe scope change, or missing authority.
  4. Require one final artifact with acceptance mapping, changed files, exact validation, diff summary, and remaining risks.
  5. Review independently without editing. Return approve or changes-requested with prioritized findings and exact evidence.
  6. Repeat implementation and review until approved; never infer approval from tests, delivery, silence, or model output.
  7. After approval, let the user create the Changeset. Commit only after explicit user authorization and a clean final validation pass.
  8. 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.
Changes

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.

  1. 12d ago First seen · 51 lines · 40 tokens per session scan A b9c0a722d5e9

Subscribe to this mod's changes

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.