file-issue

A guided workflow for turning a rough idea into a concrete GitHub issue. A GitHub issue records a problem or proposed change, including its scope and acceptance criteria.

In plain words
What is it for?
Use it to define a bug, feature, or improvement clearly enough for another coding workflow to implement.
Why use it?
It exposes missing details and checks for similar existing issues before anything is filed. It then prepares a draft for approval.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/justinthomas2/agentrc/file-issue
Any agent
npx skills add JustinThomas2/agentrc --skill file-issue
Clone the repo
git clone --depth 1 https://github.com/JustinThomas2/agentrc

Made for: Claude Code, Codex.

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 546 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00045 $0.00546
Opus 5 $0.00023 $0.00273
Sonnet 5 $0.00009 $0.00109
Haiku 4.5 $0.00005 $0.00055

Measured 2d ago against content hash 7dce787e1a3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

skills/file-issue/SKILL.md · 43 lines

What it actually says

IDEA = $ARGUMENTS — if that reads as a literal placeholder instead of a description, use the description I gave when invoking this skill. If I gave none, ask what the issue is about before doing anything else.

Issues drive the rest of the workflow: the work-issue skill reads them and works from their acceptance criteria. A vague issue degrades everything downstream, so the goal here is a draft concrete enough that work-issue can act on it without guessing.

Your task

  1. Pin down the idea. If the scope, motivation, or acceptance criteria can't be determined from what I gave, ask me BEFORE drafting — don't pad thin input into an official-looking issue.
  2. Check for duplicates with gh issue list and gh search issues (read-only). If a near-match exists — open or recently closed — show it to me and ask whether to proceed, extend that issue instead, or drop it. Never file over an existing issue.
  3. Draft the issue in this shape:
    • Title — imperative and specific
    • Problem — why this matters, what breaks or is missing today
    • Proposal — the intended change, concrete enough to implement
    • Guardrails — constraints and non-goals; omit if none apply
    • Acceptance criteria — a - [ ] checklist of verifiable outcomes the work-issue skill can work from and check off
    • End the body with the AI-attribution footer from AGENTS.md as its last line.
  4. STOP — show me the full draft (title and body) and wait for my approval. Revise per my feedback until I approve.
  5. Only after approval, file it with gh issue create. (This will ask for my approval — that is intentional; wait for it.)
  6. Reply with the issue URL. Then STOP. When I'm satisfied, I'll invoke work-issue with issue N.
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. 2d ago First seen · 43 lines · 45 tokens per session scan A 7dce787e1a3a

Subscribe to this mod's changes

file-issue is a skill published in the GitHub repository JustinThomas2/agentrc (2 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 546 once invoked, about $0.0002 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.