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 robzilla1738/roberts-skills/plugin install bughunt-suiteWrote 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/robzilla1738/roberts-skills/triage)<a href="https://agentmods.dev/commands/robzilla1738/roberts-skills/triage"><img src="https://agentmods.dev/badge/commands/robzilla1738/roberts-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 | $0.00020 | $0.00297 |
| Opus 5 | $0.00010 | $0.00148 |
| Sonnet 5 | $0.00004 | $0.00059 |
| Haiku 4.5 | $0.00002 | $0.00030 |
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 7d 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
Triage: $ARGUMENTS
Load and follow the triage skill at ${CLAUDE_PLUGIN_ROOT}/skills/triage/SKILL.md:
- Demand evidence (location, trace, trigger, impact) — anything without it is a question, not a finding.
- Assign severity (Critical/High/Medium/Low) × confidence (Confirmed/Probable/Speculative), scoring non-security findings against the impact rubric (dx/ux/performance/data-integrity/supply-chain), not just a security frame.
- For Critical/High items, build a minimal reproduction or failing test (cheapest first).
- Aggressively filter false positives; quarantine speculative items.
- Emit the standard finding schema / report layout. If you have findings as JSON (or a
.bughunt/findings.json), pipe them throughpython3 ${CLAUDE_PLUGIN_ROOT}/skills/bughunt/scripts/bughunt.py mergethenrenderto get the deduped, baseline-diffed markdown/HTML/SARIF report — see tooling.md.
Report-only — assess and prove, don't fix. If $ARGUMENTS is empty, ask for the bug or findings to triage.
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.
- 7d ago First seen · 16 lines · 20 tokens per session scan A 99822e4d7a76
triage is a command published in the GitHub repository robzilla1738/roberts-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 20 tokens to every session and 297 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
fix-issues
Diagnose, reproduce, then fix reproducible open GitHub issues in parallel: one clean worktree/issue; symlink build artifacts to avoid rebuilds.
maintainer-review-error-handling
Review the PR for error-handling correctness — surfaced errors, no silent swallows, consistent error patterns (Pi-tuned).
investigate
Establish the proven causal chain for the target — from the observed symptom to the root cause that actually explains it — and write a report a fixer or planner can act on without repeating your work. You change nothing and fix nothing: the repository must be exactly as you found it when you finish. No one watches the…
review-errors
Find one defect: a real failure crosses the changed code and becomes indistinguishable from success to the caller, operator, or user who must react. Not every error needs logging; recovery is correct when the contract permits it and the right owner can still observe the outcome. Read-only: never modify files, commit…
error-flow
Design an error flow end to end — prevention, detection, messaging, and recovery paths.
ux-fix
Opt-in fix loop. Reads the latest report from .ux/, validates working tree, and applies findings as atomic commits via the right sub-agents. Triggers on "fix the findings", "apply the fixes", or "run the fix loop". Use when applying findings from a previous audit / copy / a11y / motion / polish report, the user says…