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.
npx skills add mhmdreza-rafiei/agent-tools --skill triagegit clone --depth 1 https://github.com/mhmdreza-rafiei/agent-toolsWrote 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/skills/mhmdreza-rafiei/agent-tools/triage)<a href="https://agentmods.dev/skills/mhmdreza-rafiei/agent-tools/triage"><img src="https://agentmods.dev/badge/skills/mhmdreza-rafiei/agent-tools/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/skills/mhmdreza-rafiei/agent-tools/triage"><img src="https://agentmods.dev/badge/skills/mhmdreza-rafiei/agent-tools/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 | $0.00077 | $0.00715 |
| Opus 5 | $0.00039 | $0.00358 |
| Sonnet 5 | $0.00015 | $0.00143 |
| Haiku 4.5 | $0.00008 | $0.00072 |
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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/triage
Sort a pile of bugs/issues into a kill order before a human spends time on each one. Triage does not fix — it prioritizes and points at the likely root cause so the fixer starts close to the bug.
When to use
When the user has a list of bugs/issues (from a tracker, a log dump, a chat
thread); on /triage; before a sprint planning session.
Commands
/triage— triage the issues in context (file, paste, tracker export)./triage <file>— triage a specific file./triage update— re-triage after fixes, mark what's now resolved.
Step 1 — Read the issues
- Parse the input (one issue per line, or a tracker export). Each issue needs at minimum: a title and a symptom. If severity is already set, note it but re-derive independently.
Step 2 — For each issue, assign
- Priority —
P0(blocks users / data loss / security) /P1(major, workaround exists) /P2(minor) /P3(cosmetic). - Likely system — the subsystem the symptom points at (e.g. "auth", "payments", "build"). A guess, not a diagnosis — label it as such.
- Root-cause guess — one line, the most probable cause from the symptom.
- Duplicates — flag issues that look like the same root cause.
- Dependencies — flag issues that block or are blocked by another.
Step 3 — Kill order
Produce an ordered list: P0s first (by user impact), then P1s (by dependency order), then P2/P3 batched. Group duplicates so the fixer fixes once.
Output
## Triage
### P0
1. <issue> — likely <system>; guess: <root cause>; blocks: <ids>
### P1
2. <issue> — likely <system>; guess: <root cause>
3. <issue> — dup of #1
### P2 / P3 (batch)
- <issue>, <issue>, <issue>
Constraints
- Do not fix — that's
/recoveror the implementer. - Label root-cause guesses as guesses; never assert a diagnosis from a symptom alone.
- Trust runtime evidence (logs, repro) over issue-title wording.
Related artifacts
/context/recover(load first) — takes a P0 and diagnoses + fixes it./context/remember— save triage state for the next session.agents/qa/debugger— for issues needing deep root-cause work.
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 · 77 lines · 77 tokens per session scan A e07318b134c0
triage is a skill published in the GitHub repository mhmdreza-rafiei/agent-tools (5 stars, last pushed 24d ago), licensed MIT. It adds 77 tokens to every session and 715 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.