Borrowing it
Nothing to install: this file belongs to agigante80/actual-mcp-server. 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/agigante80/actual-mcp-server/main/.claude/skills/fork-analysis/SKILL.mdgit clone --depth 1 https://github.com/agigante80/actual-mcp-serverWrote 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/agigante80/actual-mcp-server/fork-analysis)<a href="https://agentmods.dev/skills/agigante80/actual-mcp-server/fork-analysis"><img src="https://agentmods.dev/badge/skills/agigante80/actual-mcp-server/fork-analysis/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/agigante80/actual-mcp-server/fork-analysis"><img src="https://agentmods.dev/badge/skills/agigante80/actual-mcp-server/fork-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00179 | $0.03695 |
| Opus 5 | $0.00089 | $0.01847 |
| Sonnet 5 | $0.00036 | $0.00739 |
| Haiku 4.5 | $0.00018 | $0.00369 |
Grade A, and why
fork-analysis 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 9d 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 — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fork analysis
Survey the repo's forks AND each fork's branches, identify functionality a fork
branch has that upstream lacks, and record it in docs/audit/FORK_ANALYSIS.md so the
work is not repeated next time unless that branch has actually changed. The goal
is a curated, low-noise list of ideas worth turning into tickets, not a raw diff
dump.
Branch coverage matters: a fork's default branch (main) may be a stale snapshot
while a feature/fix branch carries the real work (for example a fix/... branch
with a bug fix that never reached the fork's own main). The default-branch-only
view misses those, so analyse every meaningful branch.
This is the fork analogue of the dependency-audit cache: cheap to re-run, because unchanged branches are skipped via the recorded head sha.
When this runs
Any request to look at forks for ideas/features. Optional arguments:
- a single fork (
ownerorowner/repo) to analyse just that one, - a single
owner:branchto analyse one branch, --fullto re-analyse every branch ignoring the cache (use after a big upstream release, or if the recorded verdicts feel stale).
Everything is read-only. NEVER clone, install, build, or run fork code: a fork (or a fork branch) is untrusted. Work only from the GitHub REST API (fork list, the branches endpoint, the compare endpoint, and raw file contents fetched read-only). No em or en dashes anywhere (CLAUDE.md hard rule); convert relative dates to absolute (UTC) in the doc.
Inputs and state
REPO:agigante80/actual-mcp-server(the upstream).- The cache:
docs/audit/FORK_ANALYSIS.md. Each row is a(fork, branch)pair and records that branch'sheadsha andpushed/analysed date at the time it was last looked at, plus the verdict. A(fork, branch)whose head sha is unchanged since the last analysis is skipped (its prior verdict carries forward). Branches that share a head sha (e.g. a feature branch identical to main) are deduplicated.
Pipeline
1. Read the cache
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.
- 9d ago First seen · 273 lines · 179 tokens per session scan A 19533f84fe4e
fork-analysis is a skill published in the GitHub repository agigante80/actual-mcp-server (51 stars, last pushed yesterday), licensed MIT. It adds 179 tokens to every session and 3,695 once invoked, about $0.0009 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.
Other skills, from other repositories
code-review
Comprehensive code review assistant that analyzes code quality, security, and best practices.
verify-implementation
A workflow that runs a project’s verification skills to produce a report on coding patterns, architecture rules, and project conventions. It is intended for work after implementation, before a pull request, or during code review.
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…
red-team-review
Unified adversarial review: v4.3 Strategic Matrix (MTA-004). 7-phase framework: Priors → Rubric → Adversarial Lenses → SWOT/TOWS → MCDA Decision Engine → Blind Spot/Kill Switch → Executive Summary. Absorbs: bias-detector.
frontend-code-review
Trigger when the user requests a review of frontend files (e.g., .tsx, .ts, .js). Support both pending-change reviews and focused file reviews while applying the checklist rules.
decision-journal
Unified decision lifecycle: Pre-decision logging, post-decision review, failure classification, and calibration tracking. Absorbs: post-mortem-engine.