trace-incident

trace-incident is a skill for Claude Code, Codex from matheusPavaneli/workbench. It costs 44 tokens per session (699 once invoked), scanned A, original, MIT.

A production-incident investigation workflow that traces a reported symptom to its likely cause and records a timeline and hotfix plan. A production incident is a problem affecting the live system or its users.

In plain words
What is it for?
It helps document what happened, trace the relevant code path, collect file-and-line evidence, judge confidence in the diagnosis, and write a minimal hotfix plan.
Why use it?
It prevents rushed fixes based on guesses and separates immediate steps that limit damage from changes that remove the underlying cause.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the workbench plugin — 10 skills shipped together

Install

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.

agentmods
npx agentmods add skills/matheuspavaneli/workbench/trace-incident
Any agent
npx skills add matheusPavaneli/workbench --skill trace-incident
Clone the repo
git clone --depth 1 https://github.com/matheusPavaneli/workbench

Made for: Claude Code, Codex.

Or install workbench, the plugin that ships this one along with the rest of its 10 skills.

Wrote 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.

agentmods badge for trace-incident

README.md
[![agentmods](https://agentmods.dev/badge/skills/matheuspavaneli/workbench/trace-incident.svg)](https://agentmods.dev/skills/matheuspavaneli/workbench/trace-incident)
Your own site
<a href="https://agentmods.dev/skills/matheuspavaneli/workbench/trace-incident"><img src="https://agentmods.dev/badge/skills/matheuspavaneli/workbench/trace-incident.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 699 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00044 $0.00699
Opus 5 $0.00022 $0.00349
Sonnet 5 $0.00009 $0.00140
Haiku 4.5 $0.00004 $0.00070

Measured 3d ago against content hash cfc3b833287a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

trace-incident 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 3d 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.

skills/trace-incident/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

trace-incident

python "${CLAUDE_PLUGIN_ROOT}/lib/wb.py" <args>

The entry is a symptom — an error, an alert, a user report — not a ticket. Speed matters, which is exactly why the discipline does not loosen: a hotfix built on a guess extends the incident.

Steps

  1. Write down the symptom first, before touching code. What is observed, since when, affecting whom, and how it was noticed. This becomes the timeline in .workflow/incident-<slug>/incident.md, and it is what stops the investigation drifting to a more interesting problem than the real one.

  2. Separate stopping the bleeding from fixing the cause. They are two changes. Decide explicitly which one you are doing now. A rollback, a flag flip or a config change often beats a code fix as the immediate step — say so if it does.

  3. Trace it, do not guess it. Follow the symptom to the code path with the strongest search available: ${CLAUDE_PLUGIN_ROOT}/shared/code-search.md. Then read the actual lines. Every step of the chain from symptom to cause needs a file:line you have read.

  4. Label the confidence. A plausible cause you cannot demonstrate is a hypothesis, and calling it one is not weakness — it is the difference between a fix and a second incident. Say what would confirm it: a log line, a metric, a reproduction.

  5. Plan the smallest fix. .workflow/incident-<slug>/sdd.json, persona incident-responder, shape in ${CLAUDE_PLUGIN_ROOT}/skills/plan-change/references/sdd.md. Nothing tidied, nothing renamed, nothing upgraded. rollback states the user-visible state during and after, not just "revert the commit".

  6. Audit it anyway. sdd audit incident-<slug>. Urgency is when a wrong citation is most likely and most expensive.

  7. The regression test ships with the fix, not after. A hotfix without one is how the same incident happens twice. If it genuinely cannot be written before the fix goes out, say so explicitly and name the follow-up.

Read the full file on GitHub · 64 lines

Changes

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.

  1. 3d ago First seen · 64 lines · 44 tokens per session scan A cfc3b833287a

Subscribe to this mod's changes

trace-incident is a skill published in the GitHub repository matheusPavaneli/workbench (1 stars, last pushed 12d ago), licensed MIT. It adds 44 tokens to every session and 699 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.

Related

Other skills, from other repositories

integration-rule-engine

A declarative routing engine that turns ticket / error attributes (reporter, label, project, area path, error class, environment) into a tag + AI agent + priority assignment, so cross-source workflows ("security tickets always go to the OWASP reviewer") stay out of code and in user-editable rules.

aozyildirim/Agena · 67 tokens

stale-ticket-triage

Replace the weekly "look at every ticket older than X days" meeting with a scheduled AI scan that picks close / snooze / keep per ticket plus a one-sentence reason, so a PM can bulk-approve in 90 seconds Monday morning.

aozyildirim/Agena · 57 tokens

feature-execution

This skill should be used when the user asks to "orchestrate the feature", "run the phases", "resume implementation", "continue the plan", "the phase agent died", "the agent stopped on its usage limit", "accept this phase", "can these phases run in parallel", "is this phase done", "does this shortfall matter", or…

Langerrr/zforge · 219 tokens

dev-kit-setup

First-use bootstrap for the dev kit. Detects the team's issue tracker, discovers what it can via MCP/CLI, asks only what cannot be discovered, and persists the result to .claude/dev-kit.json in the consuming repo. Use when that file is missing, when the user asks to set up or reconfigure the kit, or when issue-fetch…

theam/claude-dev-kit · 81 tokens

pr-review

Structured review of a pull request or the current diff - correctness, contract drift, security, missing tests, coverage gate - producing classified findings and a verdict. Use when the user asks to review a PR or diff, or as the self-review step of the story workflow.

theam/claude-dev-kit · 57 tokens

acceptance-agent

Use this agent when a zforge phase has reported DONE and its evidence must be independently verified before the planner accepts it. Typical triggers include $zforge:feature-orchestrate accepting a REPORTED phase during a long chain, and any run where the planner's context is the constrained resource. It reconciles the…

Langerrr/zforge · 134 tokens