gh-issue-filing

gh-issue-filing is a skill for Claude Code from skyfox675/agents-skills. It costs 214 tokens per session (4,715 once invoked), scanned A, original, MIT.

A format and process for writing GitHub issues—requests or bug reports in a code repository—with enough evidence and criteria for an AI sub-agent to implement them.

In plain words
What is it for?
It helps create or re-triage implementation-ready issues, including file-and-line evidence, acceptance criteria, traceability, and repository labels.
Why use it?
It removes repeated clarification by recording the relevant files, exact acceptance conditions, labels, duplicates, and related work up front.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; mentions subagents.

Good fit It helps create or re-triage implementation-ready issues, including file-and-line evidence, acceptance criteria, traceability, and repository labels.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/skyfox675/agents-skills/gh-issue-filing
Install

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.

Any agent
npx skills add skyfox675/agents-skills --skill gh-issue-filing
Clone the repo
git clone --depth 1 https://github.com/skyfox675/agents-skills

Made for: Claude Code.

Wrote 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.

agentmods badge for gh-issue-filing

README.md
[![agentmods](https://agentmods.dev/badge/skills/skyfox675/agents-skills/gh-issue-filing/github.svg)](https://agentmods.dev/skills/skyfox675/agents-skills/gh-issue-filing)
Your own site
<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.

agentmods 80×15 button for gh-issue-filing

Your own site · 80×15
<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>
Per session 214 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,715 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 11d ago against content hash e7c4bbb6f732, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.

.claude/skills/gh-issue-filing/SKILL.md · 373 lines

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:P0priority: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

Read the full file on GitHub · 373 lines

Files

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.

Changes

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.

  1. 11d ago First seen · 373 lines · 214 tokens per session scan A e7c4bbb6f732

Subscribe to this mod's changes

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.