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/alejandrosaenz117/bonfires-marketplaceWrote 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/alejandrosaenz117/bonfires-marketplace/triage)<a href="https://agentmods.dev/commands/alejandrosaenz117/bonfires-marketplace/triage"><img src="https://agentmods.dev/badge/commands/alejandrosaenz117/bonfires-marketplace/triage/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/alejandrosaenz117/bonfires-marketplace/triage"><img src="https://agentmods.dev/badge/commands/alejandrosaenz117/bonfires-marketplace/triage.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 | $0.00048 | $0.01875 |
| Opus 5 | $0.00024 | $0.00937 |
| Sonnet 5 | $0.00010 | $0.00375 |
| Haiku 4.5 | $0.00005 | $0.00187 |
Grade A, and why
triage 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 12d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Reachability Triage for Dependencies
Usage: /osv-scanner triage [path]
Runs a vulnerability scan, then uses AI-powered code analysis to triage findings by likelihood of reachability. This helps you focus on CVEs that actually matter for your codebase.
⚠️ Important: Heuristic Triage
This is LLM-estimated static analysis, not deterministic call graph tracing. Useful for:
- Quick prioritization of hundreds of CVEs down to actionable items
- Understanding which vulnerabilities are low-risk for your specific codebase
- Guidance on remediation order
Not a replacement for:
- Deterministic call graph analysis (available in osv-scanner for Go and Rust via
--call-analysis) - Human security review
- Dynamic testing and runtime behavior analysis
NOT_FOUND_IN_GREP = absence of evidence, not evidence of absence. Transitive dependencies and dynamic code patterns may be reachable even when not detected by static grep search. Always treat CRITICAL/HIGH severity CVEs with caution.
How It Works
- Scan: Run
scan_vulnerable_dependencieson the provided path (defaults to workspace root) - Fetch details: For each CVE, retrieve the full advisory to identify which functions/APIs are vulnerable
- Search source code: Use Glob and Grep to find whether those specific functions are imported or called in your codebase
- Assign verdicts: Classify each finding as FOUND_IN_SOURCE, UNCERTAIN, or NOT_FOUND_IN_GREP with evidence
- Output triage report: Three-tier structured table with reasoning for each verdict
Verdict Definitions
FOUND_IN_SOURCE
The vulnerable function/method was found via grep in your source code. This CVE should be prioritized for fixing.
- Evidence: Exact file path and line number where the vulnerable API was detected
- Action: Upgrade the package, apply a patch, or change the code to avoid the vulnerable API
- Confidence: High confidence, but always verify the code path manually
UNCERTAIN
The vulnerability cannot be statically determined. This includes:
- Broad vulnerabilities affecting the entire package (not a specific function)
- Dynamic code patterns (eval, dynamic require, reflection, metaprogramming)
- Transitive dependencies (A→B→vulnerable C): grep cannot follow call chains
- Functions called through variable names or reflection
- Action: Review the advisory and your code path manually; likely mid-to-high priority depending on risk
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.
- 12d ago First seen · 135 lines · 48 tokens per session scan A 5c36952766ea
triage is a command published in the GitHub repository alejandrosaenz117/bonfires-marketplace (4 stars, last pushed 12d ago), licensed MIT. It adds 48 tokens to every session and 1,875 once invoked, about $0.0002 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 commands, from other repositories
sruja-bugfix-triage
Systematic workflow for triaging and fixing bugs with architecture grounding.
smart-help
Context-aware help that suggests relevant commands.
gws-keep
List and read Google Keep notes.
gws-people
Search and look up Google Contacts and directory profiles.
agenda
Show upcoming calendar events.
role-ops
Reliability and operations lens. Blast radius, failure, recovery.