Borrowing it
Nothing to install: this file belongs to sideralith/drydock. 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/sideralith/drydock/main/.claude/skills/drydock-issues/SKILL.mdgit clone --depth 1 https://github.com/sideralith/drydockWrote 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/sideralith/drydock/drydock-issues)<a href="https://agentmods.dev/skills/sideralith/drydock/drydock-issues"><img src="https://agentmods.dev/badge/skills/sideralith/drydock/drydock-issues/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/sideralith/drydock/drydock-issues"><img src="https://agentmods.dev/badge/skills/sideralith/drydock/drydock-issues.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 | $0.00052 | $0.00934 |
| Opus 5.5 | $0.00021 | $0.00374 |
| Sonnet 5.5 | $0.00010 | $0.00187 |
| Haiku 4.5 | $0.00005 | $0.00093 |
Grade A, and why
drydock-issues 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Activation Contract
Active when working in the drydock repo AND about to create, update, or triage a GitHub issue against it. Do NOT apply to issue work on other repos.
Hard Rules
- Use one of two templates:
.github/ISSUE_TEMPLATE/bug_report.ymlor.github/ISSUE_TEMPLATE/feature_request.yml. Do not open blank issues. - Bug template auto-applies the
buglabel; feature template auto-appliesenhancement. Do NOT add them manually. - No
status:*labels exist in this repo. Do NOT addstatus:approved,status:needs-review, etc. — that workflow belongs to agent-teams-lite, not drydock. - GitHub Issues is the ONLY intake channel for v0.1.0. No Discord, no Discussions, no mailing list. Do NOT redirect users to "Discussions".
- Bug body MUST include: command (full invocation with every flag), reproduction steps, expected behavior, actual behavior, environment (
drydockversion,docker --version, OS + version). The YAML'svalidations: required: trueblocks submission otherwise. - Feature body MUST include: problem (concrete friction first, NOT the solution), why it matters (who hits this, how often, what it costs), proposed approach (rough user-facing sketch). The
constraintsfield is where INV references and adversarial-protection justification go. - No
Co-Authored-Bytrailers in issue body (CLAUDE.md §5). - Issue title: one line describing what is broken in which command (e.g.,
drydock build fails on macOS 14 with "no such file" error).
Decision Gates
- Reporting that the host Docker socket is root-equivalent on the host? → That is INV-6 by design, NOT a vulnerability. Close as
wontfixor redirect todocs/security.md; do not file as a bug. The bug template's header already states this. - Proposing adversarial-protection (socket-proxy, gVisor, user-namespace remap, rootless Docker)? → Threat model is A (INV-7 / §4). MUST justify against a concrete real-user use case AND quantify maintenance cost on contributors. Put both in the
constraintsfield. Speculative interest or release cadence do NOT reopen the boundary. - Touching
~/.ssh/~/.gnupgmounts, or mutating host artifacts like the sibling's.git/configor~/.gitconfig? → INV-1 violation by default. Surface the conflict in the issue body and reference the affected sub-rule. - Bug vs feature ambiguity? → "broken / surprising / wrong behavior" → bug. "new capability or improvement to existing one" → feature.
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 · 48 lines · 52 tokens per session scan A 3907a5b31144
drydock-issues is a skill published in the GitHub repository sideralith/drydock (5 stars, last pushed 3mo ago), licensed MIT. It adds 52 tokens to every session and 934 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
quality
Evaluates whether a GitHub issue is spam, empty, needs more information, or is OK to proceed.
follow-up-after-call
Use after a completed customer, prospect, partner, or important internal sales call, discovery session, demo, or conversation, including when the user supplies or uploads a transcript, notes, recording summary, or other grounded evidence. Advise on, assess, qualify, recap, and produce seller-ready follow-up actions…
persona-event-coordinator
Plan and manage events — scheduling, invitations, and logistics.
persona-project-manager
Coordinate projects — track tasks, schedule meetings, and share docs.
persona-team-lead
Lead a team — run standups, coordinate tasks, and communicate.
recipe-plan-weekly-schedule
Review your Google Calendar week, identify gaps, and add events to fill them.