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 agentmods add skills/ryanjmichie-git/forgeproof-plugin/verifynpx skills add ryanjmichie-git/forgeproof-plugin --skill verifygit clone --depth 1 https://github.com/ryanjmichie-git/forgeproof-pluginWhat 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 | $0.00066 | $0.01189 |
| Opus 5 | $0.00033 | $0.00594 |
| Sonnet 5 | $0.00013 | $0.00238 |
| Haiku 4.5 | $0.00007 | $0.00119 |
Grade A, and why
verify 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 yesterday.
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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ForgeProof Verify: Bundle Integrity Check
Verify the cryptographic integrity of a ForgeProof .rpack provenance bundle.
The provenance engine script is at ${CLAUDE_PLUGIN_ROOT}/skills/run/scripts/forgeproof.py
(referenced as $FP below). Determine the Python interpreter once: run
python3 --version; if that fails or reports Python is not found, use
python. Set $FP_PY to whichever succeeded. The examples use bash syntax;
if your shell is PowerShell, adapt the invocation (& $FP_PY $FP ...).
Step 1 — Locate the bundle
If $ARGUMENTS contains a path, use it directly.
If $ARGUMENTS is empty, look for .rpack files:
ls .forgeproof/*.rpack 2>/dev/null
If multiple bundles exist, list them and ask the user which to verify. If none exist, tell the user no bundles were found.
Step 2 — Run verification
Default invocation:
"$FP_PY" "$FP" verify --rpack <path>
Add flags when the situation calls for them:
--strict— use when verifying in the origin repo or in CI, where all evidence should be present: a missing chain or missing artifacts become failures instead of warnings.--project-root <dir>— use when the bundle sits outside the project layout (by default verify anchors artifact paths to the bundle's location, falling back to the current directory).--format markdown— use when the user wants the full human audit report; relay its output verbatim instead of parsing JSON.
Example strict CI invocation:
"$FP_PY" "$FP" verify --rpack <path> --strict
Example human audit report:
"$FP_PY" "$FP" verify --rpack <path> --format markdown
Step 3 — Report results
Parse the JSON output (if you ran --format markdown, relay the report
verbatim and skip the JSON parsing). Lead the report with two keys, not one:
verified— integrity of what is present: nothing that could be checked was tampered withcomplete— completeness of the evidence set: the chain was found and no artifacts were missing
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.
- yesterday First seen · 120 lines · 66 tokens per session scan A 876395e9caa1
verify is a skill published in the GitHub repository ryanjmichie-git/forgeproof-plugin (2 stars, last pushed 11d ago), licensed MIT. It adds 66 tokens to every session and 1,189 once invoked, about $0.0003 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…