Borrowing it
Nothing to install: this file belongs to piperbox/piper. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/piperbox/piper/main/.claude/skills/file-issue/SKILL.mdgit clone --depth 1 https://github.com/piperbox/piperWrote 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/piperbox/piper/file-issue)<a href="https://agentmods.dev/skills/piperbox/piper/file-issue"><img src="https://agentmods.dev/badge/skills/piperbox/piper/file-issue/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/piperbox/piper/file-issue"><img src="https://agentmods.dev/badge/skills/piperbox/piper/file-issue.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 | $0.00041 | $0.00809 |
| Opus 5.5 | $0.00016 | $0.00324 |
| Sonnet 5.5 | $0.00008 | $0.00162 |
| Haiku 4.5 | $0.00004 | $0.00081 |
Grade A, and why
file-issue 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 2mo 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Filing an issue
Piper's tracker is public and is how contributors and future sessions see what's done and what's open. Every issue needs a title prefix and a full label set — a bare issue is an incomplete one.
Title: [area] lowercase description
The prefix names the surface the work touches, so scanning the board (or
gh issue list --search "in:title tunnel") finds everything in an area.
| Prefix | Surface |
|---|---|
[agent] |
piperd daemon: control-plane API, orchestration |
[cli] |
the piper CLI |
[deploy] |
build → run → health → route → retire flow |
[runtime] |
Docker build/run driver |
[proxy] |
Caddy routing, TLS |
[store] |
SQLite persistence |
[relay] |
piper-relay + outbound tunnel |
[repo] |
governance: CI, branch protection, tooling |
[docs] |
docs, design, README |
Reuse an existing prefix unless a genuinely new surface has appeared.
Labels: type + priority + size + binary
All four groups, every time. Note the prefixes above are not labels — the
only binary labels are agent, cli, relay.
- Type —
bug,enhancement, ordocumentation - Priority —
P1golden-path user pain ·P2real bugs, hardening, roadmap gaps ·P3cleanups, test gaps, docs, polish - Size —
size/XSa few lines ·size/Sup to ~half a day ·size/M~a day ·size/Lseveral days ·size/XLepic-scale, so split it - Binary —
agent,cli,relay; more than one is fine
Size is orthogonal to priority: small-but-P1 and large-but-P3 are both
normal. Add epic for a multi-part tracker whose sub-tasks are checkboxes
linking child issues, and the usual open-source labels (good first issue,
help wanted) where they fit.
Confirm what exists rather than guessing: gh label list.
Body
State the defect, not the fix hunt. What earns its place:
- Symptom — the observable failure, with the real error text where there is one
- Root cause — file and line, and the mechanism, when you have traced it
- A concrete failure case — the inputs or state that trigger it
- Suggested fix — only if you have one worth acting on
- Honesty about confidence — say plainly when something is derived from reading code rather than reproduced, so nobody treats an inference as observed
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.
- 2mo ago First seen · 76 lines · 41 tokens per session scan A c23b3053b40e
file-issue is a skill published in the GitHub repository piperbox/piper (10 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 41 tokens to every session and 809 once invoked, about $0.0002 per session on Opus 5.5. 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
dokku-deploy
PaaS deployment with Dokku.
coolify
Use when self-hosting apps and databases with Coolify on a VPS you own — install, first-admin lockdown, Git-to-deploy (Nixpacks/Dockerfile/compose), managed Postgres/Redis, scheduled S3 backups, domains + auto-SSL. NOT a PaaS someone else runs (that is railway), NOT sizing/hardening the box (that is hetzner), NOT…
tianji-data-query
Use when the user asks about website traffic, pageviews, monitor status, survey feedback, telemetry events, feed channels, billing usage, application stats, or other Tianji platform data through read-only queries.
tianji-worker
Use when creating, testing, deploying, invoking, debugging, scheduling, pausing, or rolling back Tianji Workers, or managing their environment variables and shared modules.
ecspresso
ECS deployment tool - deploy, manage, and troubleshoot ECS services.
clawd-media-track
Resource tracking and acquisition workflow for media resources. MUST use when the user asks to get, add, track, monitor, search, acquire, transfer, or initialize movies, TV shows, anime, Pansou resources, or 115 cloud storage items with the clawd-media-track system. For every clawd-media-track task: first read…