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 makifbaysal/tasktrooper --skill bug-report-writinggit clone --depth 1 https://github.com/makifbaysal/tasktrooperWrote 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/makifbaysal/tasktrooper/bug-report-writing)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/bug-report-writing"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/bug-report-writing/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/makifbaysal/tasktrooper/bug-report-writing"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/bug-report-writing.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 | $0.00036 | $0.00837 |
| Opus 5.5 | $0.00014 | $0.00335 |
| Sonnet 5.5 | $0.00007 | $0.00167 |
| Haiku 4.5 | $0.00004 | $0.00084 |
Grade A, and why
bug-report-writing scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
evidence: curl -X GET "$BASE/api/export?limit=10001" -H "Authorization: Bearer $TOKEN" — ran 3x, same result How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Report Writing
A defect's evidence lives in three places, each with its own job — never duplicate the full report into all three:
| Place | Contents |
|---|---|
| Failed case | actual = the observed output, verbatim. evidence = exact command/flow plus frequency, e.g. "3/3". |
| Rejected criterion note | Expected (quote the criterion), actual, reproduction, environment: short SHA, URL/base, width or device, browser/runtime. |
| need_revision comment | A numbered index, one line per defect: 1. [AC2 · case "export rejects >10k rows"] 500 instead of 422 — S2. Keep it inside the 15-line comment budget (concise-board-comments) — the reproduction lives in the criterion note and case evidence, not here. |
What fails the task
A task fails when:
- (a) a criterion or a human requirement comment is unmet;
- (b) the team UI floor is broken, by a measured threshold: horizontal overflow at any of 360/768/1024/1440, a touch target <44px at 360, an input font <16px at 360, body contrast <4.5:1, a missing loading/empty/error state on a changed view, an uncaught console error or failed request in the flow, a broken image/icon, a critical/serious axe violation inside a changed screen;
- (c) a crash, data loss, a security or authz hole, or a regression of adjacent behaviour;
- (d) a Blocker or High deviation from the approved design the task builds (design-conformance) — Medium and Nitpick are notes.
Anything else — taste, polish beyond the floor — is a note on the criterion, never a failure.
Rules
- Title names the problem, not the fix, under 60 characters: "Export of >10k rows returns 500", not "Fix export pagination".
- Isolate to the first failing step; give the minimal reproduction, not the whole scenario.
- Separate observation from speculation. A location from a stack trace or a
grep_codehit is fine (the named debugging exception); a proposed fix is not your job. - Severity, worst wins: S1 data loss/security hole > S2 broken flow (criterion unmet) > S3 degraded UX (UI-floor violation) > S4 cosmetic (never fails the task on its own — see qa-criterion-verdicts).
- Never invent a file path. A screenshot has none; describe width/URL/what-it-showed instead (ui-visual-evidence).
- One defect per case/criterion entry — do not bundle unrelated failures into one note.
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.
- 4d ago Changed · +1 lines 7c5fd8a14cd5
- 8d ago First seen · 53 lines · 36 tokens per session scan A 0742cc38fb7f
bug-report-writing is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 36 tokens to every session and 837 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-05.
Other skills, from other repositories
paperclip
Use for Paperclip-managed tasks and heartbeats: reading task context, delivering task documents or files, updating completion or blockers, coordinating or delegating work, and following company governance. Includes control plane API operations for assignments, comments, approvals, and routines.
paperclip-board
Manage a Paperclip company as a board member via chat. Use when the user wants onboarding, company or agent management, approvals, task monitoring, cost oversight, or work product review in the Paperclip control plane.
paperclip-distill
Use when an operation issue is a Paperclip cursor-window, distill, or backfill. Turn source-bundled Paperclip activity into wiki-insightful project standups, durable project pages, decisions, and history without asset dereferencing.
summarize-status
Write a short, colloquial summary for a Paperclip summary slot: open with the 1–3 specific, concrete actions the reader needs to take right now to unblock the work, then a brief plain-language status, streaming progress as it works.
paperclip-task-bridge
Create, comment on, update, and list Paperclip tasks from Hermes using scoped Paperclip API credentials.
qa-acceptance
Produce QA acceptance criteria and a manual validation plan for a feature change — golden path, edge cases, error states, performance limits, and explicit pass/fail evidence.