Borrowing it
Nothing to install: this file belongs to rjmurillo/ai-agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rjmurillo/ai-agents/main/.claude/skills/ai-agents-portability-campaign/SKILL.mdgit clone --depth 1 https://github.com/rjmurillo/ai-agentsWrote 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/rjmurillo/ai-agents/ai-agents-portability-campaign)<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/ai-agents-portability-campaign"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/ai-agents-portability-campaign/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/rjmurillo/ai-agents/ai-agents-portability-campaign"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/ai-agents-portability-campaign.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Agent Snooping · line 31 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00104 | $0.02765 |
| Opus 5 | $0.00052 | $0.01383 |
| Sonnet 5 | $0.00021 | $0.00553 |
| Haiku 4.5 | $0.00010 | $0.00277 |
Grade A, and why
ai-agents-portability-campaign 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ai-agents Portability Campaign
This skill changes hooks. agent-harness-reference owns hook facts.
ai-agents-empirical-probe-toolkit owns probe design.
ai-agents-generation-and-release owns mirror generation and the release path.
Triggers
run the portability campaignport hooks to a new harnesscopilot hook timeout regressionverify the copilot runtime contractnew copilot cli release, recheck the contract
Process
Phase 0: Load the Settled Contract
Read:
.claude/skills/agent-harness-reference/SKILL.md.claude/skills/agent-harness-reference/references/official-hook-contracts.md.claude/skills/agent-harness-reference/references/probe-evidence.md.agents/architecture/ADR-068-consolidated-hook-dispatcher.md.agents/architecture/ADR-071-plugin-hook-runtime-contract-verification.md.claude/rules/generated-artifacts.md
Do not run open-ended documentation research. Re-search or re-probe only when the reference skill's refresh rules apply.
Current load-bearing facts:
| Dimension | Settled contract |
|---|---|
| Event casing | PascalCase compatibility events deliver snake_case payloads |
| Stop | Stop is per-turn completion; SessionEnd is process lifecycle |
| PreCompact | Supported locally and in cloud automatic compaction |
| Matcher | Supported; PascalCase tool events use Claude-compatible tool names |
| PreToolUse deny | Top-level permissionDecision; nonzero denies; timeout fails open |
| PermissionRequest | behavior accepts only allow or deny; translated ask emits nothing |
| Observer output | Active PostToolUse text merges into one additionalContext; dormant SessionStart, PreCompact, and UserPromptSubmit adapters discard output; unclassified events stay direct |
| Cloud reach | Only default-branch .github/hooks/*.json loads |
| Plugin paths | Anchor through plugin-root variables; do not depend on cwd |
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.
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.
- 8d ago First seen · 281 lines · 104 tokens per session scan A 826dba704e99
ai-agents-portability-campaign is a skill published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed today), licensed MIT. It adds 104 tokens to every session and 2,765 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
auto-qa
QAMESH project QA mesh — plan, run, report, and publish deterministic QA evidence.
auto-canary
A deployment health-check skill for testing whether a recently deployed or staging website is working. It runs build, end-to-end, and browser checks, then reports a pass, warning, or failure.
verification
A verification guide for checking an implementation against its requirements and quality gates, including builds, tests, race checks, coverage, linting, and static analysis.
page-benchmark-report
Collects a small repeated benchmark for a page using Friday's readonly browser runtime.
python-mock-patching-location
Python mock.patch must target the import location, not the definition location.
config-transcription-verification
When extracting hardcoded data to JSON, field values silently drift.