bug-triage

bug-triage is a command for Claude Code from iampawan/Manifest. It costs 65 tokens per session (489 once invoked), scanned A, original, MIT.

A command for finding groups of related bugs across monitoring data, support tickets, and app-store reviews, then comparing them with existing JIRA tickets. JIRA is a system teams use to track work and bugs.

In plain words
What is it for?
Run it for one contract or for all contracts in their four-week monitoring period. It checks recent Sentry issues, clusters likely causes, and files new tickets with references.
Why use it?
It gives an up-to-date bug list, removes duplicate reports, and can create tickets for new problems instead of requiring a manual review of each source.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the manifest plugin — 28 skills, 15 commands 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 commands/iampawan/manifest/bug-triage
Clone the repo
git clone --depth 1 https://github.com/iampawan/Manifest

Made for: Claude Code.

Or install manifest, the plugin that ships this one along with the rest of its 28 skills, 15 commands.

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 bug-triage

README.md
[![agentmods](https://agentmods.dev/badge/commands/iampawan/manifest/bug-triage.svg)](https://agentmods.dev/commands/iampawan/manifest/bug-triage)
Your own site
<a href="https://agentmods.dev/commands/iampawan/manifest/bug-triage"><img src="https://agentmods.dev/badge/commands/iampawan/manifest/bug-triage.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 489 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 5.1 $0.00065 $0.00489
Opus 5 $0.00032 $0.00244
Sonnet 5 $0.00013 $0.00098
Haiku 4.5 $0.00006 $0.00049

Measured 6d ago against content hash 7ff2869cf737, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

bug-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 6d 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.

commands/bug-triage.md · 56 lines

What it actually says

/bug-triage

Invokes the bug-triage skill against the given contract.

Usage

/bug-triage <ID>                  # scope to one contract
/bug-triage                       # all contracts currently in their 4-week landing window

When to use it manually

The bug-triage skill normally runs every day automatically via the launch-monitor.yml cron. You'd run it manually when:

  • A known incident just happened and you want fresh data before the next cron tick.
  • You're preparing for a stakeholder update and want today's bug list, not yesterday's.
  • You're piloting Manifest without CI workflows installed yet and the cron isn't firing — manual is your only option.
  • You're testing changes to the bug-triage skill itself.

What it does

  1. Reads .manifest/contracts/*.md to find contracts currently in their 4-week monitoring window.
  2. For each: queries Sentry for new issues in the last 24h filtered to that release.
  3. Pulls qualitative signals from JIRA / support tools / app store reviews (if those MCPs are connected).
  4. Clusters findings by likely root cause.
  5. Dedupes against existing JIRA tickets (via Atlassian MCP).
  6. Files new tickets with contract back-references, severity, and reproduction steps inferred from stack traces.
  7. Appends to .manifest/contracts/<ID>.bug-log.md.
  8. Posts a daily summary to the contract's Slack thread.

Output

A markdown bug-log entry per affected contract, plus JIRA tickets filed, plus a Slack summary.

Anti-patterns

  • Don't run this repeatedly in quick succession (the dedup logic handles overlap but you'll just be re-confirming the same data).
  • Don't use this as a real-time error monitor — it's a daily-rhythm tool. Sentry alerting is the real-time path.
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. 6d ago First seen · 56 lines · 65 tokens per session scan A 7ff2869cf737

Subscribe to this mod's changes

bug-triage is a command published in the GitHub repository iampawan/Manifest (5 stars, last pushed 3d ago), licensed MIT. It adds 65 tokens to every session and 489 once invoked, about $0.0003 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.