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/adolfousier/opencrabs/githubnpx skills add adolfousier/opencrabs --skill githubgit clone --depth 1 https://github.com/adolfousier/opencrabsWhat 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 | $0.00065 | $0.01580 |
| Opus 5 | $0.00032 | $0.00790 |
| Sonnet 5 | $0.00013 | $0.00316 |
| Haiku 4.5 | $0.00006 | $0.00158 |
Grade A, and why
github scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Do NOT proceed without auth. Do NOT fall back to `curl` or `http_request`. How it starts
The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Skill
Full GitHub operations via the gh CLI. Always check auth first, use templates for consistency, and respect rate limits.
Step 0: Auth Detection (ALWAYS FIRST)
Before ANY GitHub operation, detect the auth method:
gh auth status 2>&1
If authenticated: Proceed. Note the logged-in username for the session.
If not authenticated: Check for GITHUB_TOKEN env var:
echo "${GITHUB_TOKEN:+token_set}"
If no token either: Tell the user:
GitHub CLI is not authenticated. Run
gh auth loginto authenticate, or setGITHUB_TOKENenvironment variable with a personal access token.
Do NOT proceed without auth. Do NOT fall back to curl or http_request.
Step 1: Rate Limit Check (before bulk operations)
Before operations that issue 5+ API calls (batch triage, bulk label, multi-issue create), check rate limits:
gh api rate_limit --jq '.resources.core.remaining, .resources.core.limit, .resources.search.remaining, .resources.search.limit'
If core remaining < 100 or search remaining < 10, warn the user and ask whether to proceed.
Issue Operations
Create Issue
gh issue create --repo OWNER/REPO --title "TITLE" --body "BODY" --label "LABEL" --assignee "USER"
Templates (use unless user provides their own):
Bug report:
## Description
[What happened]
## Steps to Reproduce
1. [Step 1]
2. [Step 2]
## Expected Behavior
[What should happen]
## Actual Behavior
[What actually happened]
## Environment
- OS: [e.g., macOS 14.3]
- Version: [e.g., v0.3.70]
Feature request:
## Problem
[What problem does this solve?]
## Proposed Solution
[How should it work?]
## Alternatives Considered
[What else was considered?]
## Additional Context
[Screenshots, logs, references]
List Issues
gh issue list --repo OWNER/REPO --state open --limit 20
gh issue list --repo OWNER/REPO --label "bug" --state open
gh issue list --repo OWNER/REPO --assignee "@me"
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 · 265 lines · 0 tokens per session scan A 16b44c290eef
github is a skill published in the GitHub repository adolfousier/opencrabs (916 stars, last pushed 2d ago), licensed MIT. It adds 65 tokens to every session and 1,580 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
compare-harnesses
Diff two scaffolded harnesses (ADR-031). Reports manifest meta drift + host list + per-file fingerprint changes (added/removed/changed). Exits 0 IDENTICAL, 1 DRIFT, 2 missing manifest. Use --bundle for the ADR-031 schema-1 JSON envelope.
create-harness
Scaffold your own focused AI agent harness — pick host (Claude Code, Codex, pi.dev, Hermes), template, agents, skills, and ship a npm-publishable harness with its own npx CLI. Use when a user asks to "create my own agent harness", "scaffold a harness", "make a custom Claude Code plugin like ruflo", or "build a…
diag-harness
Kernel-version skew check (ADR-027). Reports manifest surface + manifest kernel + installed kernel + verdict (match/patch-diff/minor-diff/major-diff). Exits 1 on minor/major skew with a copy-pasteable npm install @metaharness/[email protected] next step. Exits 2 if no .harness/manifest.json at path.
oia-manifest
Emit .harness/oia-manifest.json declaring layer alignment with the OIA v0.1 9-layer reference architecture. Self-describes the harness's MCP wiring, witness signing, audit log, identity posture (always 'none' at v0.1). --check verifies an existing manifest, --dry-run prints without writing, --json emits to stdout.
repo-genome
7-section readiness scorecard for a LOCAL repo. Reports repo type + agent topology + MCP risk + test confidence + release readiness + recommended harness plan + scorecard. Exit 0 ready, 1 needs-work, 2 blocked. --json for the 6-field scorecard, --bundle for the ADR-031 schema-1 envelope.
example-harness
Scaffold a ready-made AI agent harness in one command from the 19 published @metaharness/ example packages — 9 host integrations (Claude Code, Codex, Hermes, pi.dev, OpenClaw, RVM, Copilot, OpenCode, GitHub Actions) + 10 vertical pods (devops, research, trading, support, legal, coding, education, sales, gaming…