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 skyfox675/agents-skills --skill gh-issue-filinggit clone --depth 1 https://github.com/skyfox675/agents-skillsWrote 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/skyfox675/agents-skills/gh-issue-filing)<a href="https://agentmods.dev/skills/skyfox675/agents-skills/gh-issue-filing"><img src="https://agentmods.dev/badge/skills/skyfox675/agents-skills/gh-issue-filing/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/skyfox675/agents-skills/gh-issue-filing"><img src="https://agentmods.dev/badge/skills/skyfox675/agents-skills/gh-issue-filing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 3 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 49 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00214 | $0.04715 |
| Opus 5 | $0.00107 | $0.02357 |
| Sonnet 5 | $0.00043 | $0.00943 |
| Haiku 4.5 | $0.00021 | $0.00471 |
Grade A, and why
gh-issue-filing 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 11d 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 — 373 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Filing GitHub Issues That Agents Can Ship
Issues filed here feed the multi-agent pipeline (claimed per gh-issue-locking, dispatched per dispatching-subagents, scheduled per orchestrating-slots, merged per driving-prs-to-merge; labels per gh-issue-labels). This skill covers both ends of intake: writing groomed issues, and recon-triaging stubs.
Project bindings
Define these once in the adopting project's CLAUDE.md, alongside the sibling skills' shared bindings (integration branch, worktree convention, toolchain bootstrap, CI gate names, bot reviewers, operator logins). The body refers to them by placeholder; example values are illustrations, not requirements.
| Binding | Meaning | Example |
|---|---|---|
<repo-slug> |
--repo target for gh commands |
acme/widgets |
<type-labels> |
exactly-one type label set | bug, enhancement |
<priority-labels> |
exactly-one priority ladder | priority:P0…priority:P3 |
<security-label> |
flag for authn/authz/data-isolation/OWASP-class issues | security |
<lane-labels> |
shared-surface vs isolated work | lane:plumbing, lane:leaf |
<component-labels> |
component/subsystem label namespace | subsystem:* |
<triage-labels> |
terminal triage states | ready-to-dispatch, needs-spec-input, blocked |
<claim-label> / <hold-label> |
active-work lock (gh-issue-locking) / operator hold (gh-issue-labels); neither applied at filing | agent-claimed / do-not-dispatch |
<breaking-change-labels> |
CI breaking-change acknowledgment gates, if any | db:… / api:breaking-change-acknowledged |
<traceability-scheme> |
requirement-ID format + doc location, if formal traceability exists | REQ-<PREFIX>-<N> in docs/specs/ |
<shared-surfaces> |
enumerated contention-prone files defining the plumbing lane | DB schema, new migrations, API schema, design tokens, shared-types package, root manifest/lockfile |
<crown-jewel-invariant> |
hardest invariant; mentioning it auto-escalates to P0 | "tenant isolation" |
<subsystem-tiers> |
security-critical (auto-P0) / core (partial → P1) / deferred (auto-stall without logged decisions) | auth/payments vs core feature modules vs deferred/experimental areas… |
<decision-records> |
where architectural decisions for deferred areas are logged | docs/specs/_subsystems/ |
<design-source> |
UI source of truth a UI spec must anchor to | design-system/ folder |
<cheap-model> / <default-model> |
recon model tier / escalation tier | haiku / sonnet |
<second-tracker> |
optional second tracker + ref syntax; route by where work was filed | Jira, Refs PROJ-N |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 373 lines · 214 tokens per session scan A e7c4bbb6f732
gh-issue-filing is a skill published in the GitHub repository skyfox675/agents-skills (10 stars, last pushed 10d ago), licensed MIT. It adds 214 tokens to every session and 4,715 once invoked, about $0.0011 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
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
shiplog
Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.
llxprt-issue-workflow
Use this skill when asked to address, fix, or work on a GitHub issue in the llxprt-code repository. Covers the complete issue lifecycle - branch setup, gh CLI usage, test-first planning, subagent delegation and review loops, the full verification cycle (including the stepfun-37 smoke test), open code review (ocr), PR…
cyrus-setup-repository
Add one or more Git repositories to Cyrus configuration so it can process issues from those repos.
github-sync
Bidirectional synchronization of epics and tasks with GitHub issues, labels, and relationships.
github-notification-triage
Triage GitHub notifications and issue/PR queues.