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.
git clone --depth 1 https://github.com/ThierryN/fire-flowWrote 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/thierryn/fire-flow/fire-security-audit-repo)<a href="https://agentmods.dev/commands/thierryn/fire-flow/fire-security-audit-repo"><img src="https://agentmods.dev/badge/commands/thierryn/fire-flow/fire-security-audit-repo/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/thierryn/fire-flow/fire-security-audit-repo"><img src="https://agentmods.dev/badge/commands/thierryn/fire-flow/fire-security-audit-repo.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 | $0.00020 | $0.02412 |
| Opus 5 | $0.00010 | $0.01206 |
| Sonnet 5 | $0.00004 | $0.00482 |
| Haiku 4.5 | $0.00002 | $0.00241 |
Grade C, and why
fire-security-audit-repo scanned grade C with 6 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.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
grep -rnE '(rm -rf|sudo |chmod 777|eval\(|exec\()' /tmp/{name}-security-review/ Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Reaches for credential filesmediumPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
grep -rnE '(\.env|\.ssh|\.aws|credentials|\.gnupg|\.netrc)' /tmp/{name}-security-review/ --include='*.md' --include='*.sh' --include='*.js' Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Enumerates other installed skillslowAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
bash ~/.claude/hooks/credential-filter.sh --dir ~/.claude/skills/{name}/ Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
grep -rnE '(rm -rf|sudo |chmod 777|eval\(|exec\()' /tmp/{name}-security-review/ Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
grep -rnE '(curl |wget |nc |ncat )' /tmp/{name}-security-review/ --include='*.sh' --include='*.md' Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
grep -rnE '(child_process|os\.system|subprocess|spawn\()' /tmp/{name}-security-review/ --include='*.js' --include='*.ts' --include='*.py' How it starts
The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fire-security-audit-repo — Pre-Install Security Audit
Audit any GitHub repo for security threats before installing it as a Claude Code skill or plugin.
Purpose
Prevent supply chain attacks by running a 6-layer security audit on any GitHub repository before it enters the agent's trusted execution environment. This is the pre-download and pre-use gate.
Process
Step 1: Pre-Download Intelligence
Before cloning, gather repo metadata:
# Parse repo from URL or owner/name format
REPO="{owner}/{name}"
# Gather intelligence
gh repo view $REPO --json stargazersCount,forkCount,createdAt,updatedAt,licenseInfo,description,isArchived
gh api repos/$REPO/commits?per_page=5 --jq '.[].commit.message'
gh api users/{owner} --jq '{login, created_at, public_repos, followers}'
Display pre-download report:
+------------------------------------------------------------------------------+
| FIRE SECURITY AUDIT — PRE-DOWNLOAD |
+------------------------------------------------------------------------------+
| |
| Repo: {owner}/{name} |
| Description: {description} |
| Stars: {N} Forks: {N} License: {license} |
| Created: {date} Last updated: {date} |
| Owner: {login} ({public_repos} repos, {followers} followers, since {date}) |
| |
| Recent commits: |
| - {message 1} |
| - {message 2} |
| - {message 3} |
| |
+------------------------------------------------------------------------------+
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 · 294 lines · 20 tokens per session scan C a21a67d99935
fire-security-audit-repo is a command published in the GitHub repository ThierryN/fire-flow (77 stars, last pushed 27d ago), licensed MIT. It adds 20 tokens to every session and 2,412 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 6 findings (asks for root, reaches for credential files, enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
export-closedloop-learnings
Exports pending ClosedLoop learnings to global location with deduplication.
review
Review the current diff against project memory.
help
Quick reference for all Attune commands.
tdd
Test-driven change — write the failing test first, then implement.
lfe-improve-architecture
Find deepening opportunities in the codebase — turn shallow modules into deep ones. Use in Phase 5 (Hygiene sub-pipeline) or when scheduled by session count.
lfe-plan-critique
Run a 5-lens pre-build critique of the approved active plan before the Builder starts. Acts as the Architect persona, read-only on src/. Writes .plans/plancritique.md. Use immediately after Brain approves activeplan.md.