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/Jewgah/claude-code-skillsWrote 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/jewgah/claude-code-skills/triage)<a href="https://agentmods.dev/commands/jewgah/claude-code-skills/triage"><img src="https://agentmods.dev/badge/commands/jewgah/claude-code-skills/triage.svg" alt="Measured on agentmods" 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 | $0.00027 | $0.00413 |
| Opus 5 | $0.00014 | $0.00206 |
| Sonnet 5 | $0.00005 | $0.00083 |
| Haiku 4.5 | $0.00003 | $0.00041 |
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 8d 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.
What it actually says
Source: $ARGUMENTS
Run this as the main session (you can dispatch sub-agents). If a referenced agent isn't installed (minimal tier), do that step yourself inline.
- Read the report — if
$ARGUMENTSis a file path (PDF,.md,.txt), read it (the Read tool handles PDFs); if it's a pasted list, use it as-is. If empty, ask me for the path. - Extract & list — turn it into a checklist with TodoWrite: one item per distinct issue, each with a short title + the reported symptom + any repro/location hints.
- Triage — tag each issue
CRITICAL/HIGH/NORMAL/LOW. Flag anything ambiguous or needing a product decision as needs-info and do NOT fix it — surface it for me to resolve. - Fix loop — in priority order, for each actionable issue: dispatch
explorer(locate + root cause) →implementer(minimal fix) →tester({{TEST_CMD}}); add areviewerpass if the fix is risky. Update each todo as you go. If there are many issues, auto-handleCRITICAL+HIGHand pause to ask beforeNORMAL/LOW— unless I said do all. - Don't commit or push unless I ask.
End with a triage summary table: Issue | Severity | Status (fixed / deferred / needs-info) | Root cause + fix (path:line). Then append the Dispatch report: Why this config, the per-agent table Agent | Why popped | What it did | Result, and Skipped.
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.
- 8d ago First seen · 17 lines · 27 tokens per session scan A 0a8d021c9fd8
triage is a command published in the GitHub repository Jewgah/claude-code-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 413 once invoked, about $0.0001 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
modernize-transform
Transform one legacy module to the target stack — idiomatic rewrite with behavior-equivalence tests.
trace
Trace the execution path of a request or operation through the codebase.
debug-pod
Debug a failing or unhealthy Kubernetes pod by analyzing events, logs, and configuration.
map
Generate a dependency map showing how modules and files relate to each other in the codebase.
root-cause
Use when any test fails, bug appears, or behaviour surprises you, before proposing a fix - find the cause and prove it, by reading real evidence, tracing bad values back to their origin, comparing against a working case, and testing one hypothesis at a time.
find-dead-code
Identify unused code across the codebase.