Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add ogrodev/fsociety/plugin install tyrellWrote 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/commands/ogrodev/fsociety/ty-github)<a href="https://agentmods.dev/commands/ogrodev/fsociety/ty-github"><img src="https://agentmods.dev/badge/commands/ogrodev/fsociety/ty-github/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/commands/ogrodev/fsociety/ty-github"><img src="https://agentmods.dev/badge/commands/ogrodev/fsociety/ty-github.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00015 | $0.00970 |
| Opus 5.5 | $0.00006 | $0.00388 |
| Sonnet 5.5 | $0.00003 | $0.00194 |
| Haiku 4.5 | $0.00002 | $0.00097 |
Grade C, and why
ty-github scanned grade C with 2 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 2mo 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf /tmp/tyrell-scan-$$ Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -H "Authorization: Bearer ${GITHUB_TOKEN}" \ How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are executing a GitHub/GitLab leak scan for the tyrell data exfiltration plugin.
Step 1 — Generate Search Queries
Run the hunt engine to produce optimized code repository search queries:
node "${CLAUDE_PLUGIN_ROOT}/scripts/hunt-engine.js" github $ARGUMENTS
The script returns query objects with fields: platform (github|gitlab), query, type, file_extensions, and rationale. Query types cover secrets, config files, database dumps, and environment files.
Step 2 — Execute GitHub Code Search
For each query targeting GitHub:
# Via GitHub CLI (preferred)
gh search code "<query>" --limit 50 --json repository,path,url,textMatches
# Via GitHub REST API (fallback)
curl -s -H "Authorization: Bearer ${GITHUB_TOKEN}" \
-H "Accept: application/vnd.github.v3+json" \
"https://api.github.com/search/code?q=<url-encoded-query>&per_page=50" | \
jq '.items[] | {repo: .repository.full_name, path: .path, url: .html_url}'
Step 3 — Execute GitLab Search
For each query targeting GitLab:
curl -s -H "PRIVATE-TOKEN: ${GITLAB_TOKEN}" \
"https://gitlab.com/api/v4/search?scope=blobs&search=<url-encoded-query>" | \
jq '.[] | {project: .project_id, filename: .filename, ref: .ref, startline: .startline}'
Step 4 — Deep-Scan Identified Files
For each promising file returned by search results, fetch and analyze its content:
# Fetch raw file content from GitHub
curl -s -H "Authorization: Bearer ${GITHUB_TOKEN}" \
"https://raw.githubusercontent.com/<owner>/<repo>/<branch>/<path>"
# Clone and scan with gitleaks (if repo is public)
git clone --depth=1 "https://github.com/<owner>/<repo>" /tmp/tyrell-scan-$$
gitleaks detect --source=/tmp/tyrell-scan-$$ --report-format=json --report-path=/tmp/gitleaks-$$.json
cat /tmp/gitleaks-$$.json | jq '.[] | {rule: .RuleID, file: .File, secret: .Secret, commit: .Commit}'
rm -rf /tmp/tyrell-scan-$$
For secrets detection with trufflehog:
trufflehog github --repo="https://github.com/<owner>/<repo>" --json 2>/dev/null | \
jq '{detector: .DetectorName, verified: .Verified, raw: .Raw, file: .SourceMetadata.Data.Github.file}'
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.
- 2mo ago First seen · 106 lines · 15 tokens per session scan C 7029d78e63a3
ty-github is a command published in the GitHub repository ogrodev/fsociety (20 stars, last pushed 7mo ago), licensed MIT. It adds 15 tokens to every session and 970 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
replay
You are reconstructing the historical evolution of this sprint by recompiling every version of claims.json from git history.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
commit
Create well-formatted commits with conventional commit messages and emojis.
genshijin-commit
A command that writes a commit message for changes already placed in Git's staging area. It follows the repository's existing language and uses a short imperative subject without AI attribution.
commit
Smart conventional commit with security validation, branch flow enforcement, and auto-detection. Use for git commit, commit changes, save work, stage and commit.
flow
Universal workflow entry point. Use /flow for skill-driven GitHub development. Verbs: start, commit, pr, review, address, merge, resolve, release, status, learn, setup, explain, debug, design, brainstorm, issue, goal, resume, run, trigger, watch, workflow.