experience-pr

experience-pr is a skill for Claude Code, Codex from FoloToy/ai-passport. It costs 31 tokens per session (1,797 once invoked), scanned A, original, MIT.

A procedure for collecting reusable lessons from a FoloToy firmware release and proposing them as documentation changes in the upstream ai-passport project. It prepares a pull request only after consent and access checks.

In plain words
What is it for?
Use it after a release when the developer asks to capture development experience and submit or prepare the resulting documentation update.
Why use it?
It turns release-specific experience into project documentation while avoiding changes to the current branch and avoiding submission when no GitHub channel is available.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it after a release when the developer asks to capture development experience and submit or prepare the resulting documentation update.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/folotoy/ai-passport/experience-pr
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 FoloToy/ai-passport --skill experience-pr
Clone the repo
git clone --depth 1 https://github.com/FoloToy/ai-passport

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 experience-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/folotoy/ai-passport/experience-pr/github.svg)](https://agentmods.dev/skills/folotoy/ai-passport/experience-pr)
Your own site
<a href="https://agentmods.dev/skills/folotoy/ai-passport/experience-pr"><img src="https://agentmods.dev/badge/skills/folotoy/ai-passport/experience-pr/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 experience-pr

Your own site · 80×15
<a href="https://agentmods.dev/skills/folotoy/ai-passport/experience-pr"><img src="https://agentmods.dev/badge/skills/folotoy/ai-passport/experience-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,797 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
SkillSpector: 1 finding, up to low

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • low Excessive Agency · line 121
    Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.
    Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 $0.00031 $0.01797
Opus 5 $0.00015 $0.00898
Sonnet 5 $0.00006 $0.00359
Haiku 4.5 $0.00003 $0.00180

Measured 6d ago against content hash bc1194c4a2be, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

experience-pr 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 6d 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.

skills/experience-pr/SKILL.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Collect Development Experience and Submit a PR

This skill captures the reusable, durable learnings from a firmware release and proposes them as a documentation pull request to the upstream FoloToy/ai-passport project. It runs only after a release and only when the developer explicitly asks to collect experience.

Do not collect, draft, or submit anything until every gate below is satisfied. These gates are the highest-priority constraints.

  1. Confirm consent up front. This work touches project-private content. Ask the developer to confirm they agree to start the post-release follow-up before collecting anything. If they decline, stop immediately.
  2. Check GitHub access. Confirm a GitHub channel is available before submitting. Try the configured channels in order and use the first one that works: GitHub MCP (when present and authenticated), a GitHub skill (for example the installed cindy-github capability), then the gh CLI (gh auth status). If none is available, generate the complete change content for the developer to paste manually and stop; never submit on their behalf.
  3. Never modify or commit on the current branch. The release experience is usually derived from the current working branch, but the change must not be committed on the developer's current branch. Base the work on the latest upstream main for a clean baseline, create a dedicated branch or worktree, push it to the developer's fork (origin), and open the PR from that fork branch against the upstream FoloToy/ai-passport. Leave the current checkout untouched.
  4. Never submit before review. Draft everything first, show it to the developer, and wait for explicit approval. Do not commit, push, or open a PR until the developer has reviewed and authorized it. Opening a PR also requires separate confirmation.
  5. No credentials or private data. Never include credentials, device QR secrets, private device links, personal data, or unsanitized logs. Run python3 tools/check_repo.py before committing anything.

Read the full file on GitHub · 169 lines

Files

What ships with it

1 file 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. 6d ago Changed bc1194c4a2be
  2. 10d ago First seen · 169 lines · 31 tokens per session scan A e843d99edfef

Subscribe to this mod's changes

experience-pr is a skill published in the GitHub repository FoloToy/ai-passport (279 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 1,797 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.