proofslip: Skill for Codex

.agents/skills/proofslip-release-proof/SKILL.md

proofslip-release-proof is a skill for Codex from Johnny-Z13/proofslip. It costs 84 tokens per session (707 once invoked), scanned A, original, MIT.

A tool for checking whether a ProofSlip release record matches the deployment evidence from GitHub Actions, GitHub's service for running automated build and deployment jobs.

In plain words
What is it for?
Use it to verify a proof ID or URL, assess a claim that a release was deployed, or prepare the minimal GitHub Actions setup needed to add release proof.
Why use it?
It separates facts confirmed by GitHub from observations recorded by ProofSlip and information merely supplied by someone, so an agent does not treat an unsupported shipping claim as verified.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents).

This is Johnny-Z13/proofslip's own configuration. It tells Codex how to work on proofslip itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything proofslip configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Johnny-Z13/proofslip. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Johnny-Z13/proofslip/master/.agents/skills/proofslip-release-proof/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Johnny-Z13/proofslip

Made for: 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 proofslip-release-proof

README.md
[![agentmods](https://agentmods.dev/badge/skills/johnny-z13/proofslip/proofslip-release-proof.svg)](https://agentmods.dev/skills/johnny-z13/proofslip/proofslip-release-proof)
Your own site
<a href="https://agentmods.dev/skills/johnny-z13/proofslip/proofslip-release-proof"><img src="https://agentmods.dev/badge/skills/johnny-z13/proofslip/proofslip-release-proof.svg" alt="Measured on agentmods" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 707 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.
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 $0.00084 $0.00707
Opus 5 $0.00042 $0.00353
Sonnet 5 $0.00017 $0.00141
Haiku 4.5 $0.00008 $0.00071

Measured 7d ago against content hash 18803613643f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

proofslip-release-proof 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 7d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/verify-proof.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/skills/proofslip-release-proof/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ProofSlip Release Proof

Separate provider-verified facts, ProofSlip observations, and submitted context. Never collapse them into a generic “verified deployment” claim.

Choose the workflow

  • For a proof ID or URL, verify the existing proof.
  • For a request to add release proof, inspect the repository and prepare the GitHub Actions change.
  • For a vague shipping claim without a proof, explain that the claim is currently unverified and offer the setup workflow.

Verify an existing proof

  1. Run:

    node <skill-dir>/scripts/verify-proof.mjs <proof-id-or-url>
    

    Replace <skill-dir> with this skill directory. For an explicitly trusted self-hosted instance, add --base-url https://host.example.

  2. Stop if the script reports unverifiable or invalid, or if the repository, commit, ref, workflow, run, or event does not match the release task at hand.

  3. Report these evidence lanes separately:

    • Provider verified: repository, commit SHA, ref, workflow, run, actor, and event from GitHub Actions OIDC.
    • ProofSlip observed: bounded HTTP observations made by ProofSlip, including failures and timestamps.
    • Submitted, not verified: labels and context supplied by the workflow.
  4. State the limitations from references/release-proof-contract.md.

  5. Compare the verified repository, SHA, ref, workflow, run, and event with the current task before allowing downstream work to rely on the proof.

Add release proof to GitHub Actions

  1. Inspect the repository root, current branch, working tree, and .github/workflows/ without changing them.
  2. Identify the existing workflow and job that actually performs the release. Do not create a detached “proof” workflow that runs independently of the release it describes.
  3. Read references/release-proof-contract.md and assets/proofslip-release-proof-step.yml.
  4. Propose the smallest patch:
    • add id-token: write and contents: read permissions;
    • add the ProofSlip step only after the release and required checks succeed;
    • keep the OIDC token ephemeral and masked;
    • send no ProofSlip API key;
    • include a deployment observation only for an explicit public HTTPS target;
    • write the returned proof URL to the GitHub Actions job summary.
  5. Ask for approval before editing workflow files. Treat workflow permissions as security-sensitive.
  6. After approval, adapt the bundled step to the repository rather than copying placeholders unchanged.
  7. Validate the YAML and existing repository checks. Do not commit, push, run a release, or change production without separate authorization.

Read the full file on GitHub · 61 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 61 lines · 84 tokens per session scan A 18803613643f

Subscribe to this mod's changes

proofslip-release-proof is a skill published in the GitHub repository Johnny-Z13/proofslip (1 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 707 once invoked, about $0.0004 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.