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 iampawan/Manifest --skill bug-triagegit clone --depth 1 https://github.com/iampawan/ManifestWrote 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/iampawan/manifest/bug-triage)<a href="https://agentmods.dev/skills/iampawan/manifest/bug-triage"><img src="https://agentmods.dev/badge/skills/iampawan/manifest/bug-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 | $0.00082 | $0.01790 |
| Opus 5 | $0.00041 | $0.00895 |
| Sonnet 5 | $0.00016 | $0.00358 |
| Haiku 4.5 | $0.00008 | $0.00179 |
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 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug triage agent
You run alongside the launch reports. Each invocation looks for new bug clusters across error tracking and user-facing channels, dedupes against already-filed tickets, and creates new tickets with proper context.
Inputs
- Optional: contract ID (scope to one feature). If omitted, scan all contracts currently in their landing window.
- Time window: default last 24 hours.
Process
1. Identify contracts in monitoring
Read .manifest/contracts/*.md. Find contracts where:
landedis not yet set (still in monitoring window), ORlandingTrackcontains a verdict from the last 28 days
These are the features you're responsible for.
2. Pull errors from Sentry
Use the Sentry MCP to query:
- New issues in the last 24h
- Filtered to release tags matching contracts in monitoring
- OR filtered to source paths touched in implementation plans
For each new issue, extract: error class, count, affected users, first seen, stack trace top frame, code locations.
3. Pull qualitative signals
If support tool MCPs are connected:
- New tickets in the last 24h
- Search for keywords from contract titles + feature flag names
If app store review MCPs are connected (App Store Connect / Play Console):
- New 1-2 star reviews mentioning feature-relevant keywords
4. Cluster
Group findings by likely root cause. Two errors with the same top frame or the same component name are likely one cluster. Two support tickets describing the same confusion are one cluster.
For each cluster:
- Severity (S0..S3 by your team's convention)
- Affected user count estimate
- Likely related contract / behavior
- Probable bug category: functionality / comms / UI / perf
5. Deduplicate against JIRA
Use the Atlassian MCP to search for existing tickets with overlapping
- error class
- contract reference
- date range
If a match found, update the existing ticket with new evidence (+1 occurrences, add the new affected users). Don't create duplicates.
6. File new tickets
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 · 175 lines · 82 tokens per session scan A 9005cabd4983
bug-triage is a skill published in the GitHub repository iampawan/Manifest (5 stars, last pushed 6d ago), licensed MIT. It adds 82 tokens to every session and 1,790 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 2026-08-31.
Other skills, from other repositories
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
triage-issue
Intelligently triage bug reports and error messages by searching for duplicates in Jira and offering to create new issues or add comments to existing ones. When an agent needs to: (1) Triage a bug report or error message, (2) Check if an issue is a duplicate, (3) Find similar past issues, (4) Create a new bug ticket…
bug-triage
Read all open bugs in production/qa/bugs/, re-evaluate priority vs. severity, assign to sprints, surface systemic trends, and produce a triage report. Run at sprint start or when the bug count grows enough to need re-prioritization.
investigation
Create an investigation ticket + live-doc for sustained root-cause work (retros, bug archaeology, regression hunts).
browse-flows
Browse Power Automate environments and flows interactively. Use when the user wants to browse, list, or explore their flows and environments.
operating-cadence
Designs the rhythm an organization runs on — which reviews happen weekly, monthly and quarterly, what each one decides, who owns the numbers presented, and how a signal at the front line reaches the people who can act on it. Use this to set up a management operating system, fix a meeting calendar that produces no…