report-issue

A guide-maintenance skill for investigating a real problem encountered while following a step-by-step developer guide.

In plain words
What is it for?
Use it to locate an issue, repair the relevant instructions, scan the rest of the guide, and record the report and fix.
Why use it?
It fixes the underlying guide error and looks for other places where the same mistake could cause trouble.

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/tomthebearded/guide-forge/report-issue
Any agent
npx skills add tomthebearded/guide-forge --skill report-issue
Clone the repo
git clone --depth 1 https://github.com/tomthebearded/guide-forge

Made for: Claude Code, Codex.

Per session 191 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 749 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 $0.00191 $0.00749
Opus 5 $0.00096 $0.00375
Sonnet 5 $0.00038 $0.00150
Haiku 4.5 $0.00019 $0.00075

Measured 2d ago against content hash b35be161d4b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

report-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/report-issue/SKILL.md · 50 lines

What it actually says

Skill: report-issue

The complete, canonical contract for this skill is the paste-prompt it wraps, inlined here — follow it in full:

!cat "${CLAUDE_SKILL_DIR}/prompt.md"

(If the block above came back empty or errored, read prompt.md in this skill folder — it sits beside this SKILL.md — and follow that.)

As you follow it, adapt for the fact that you're a Claude Code skill, not a pasted prompt:

  • You're already invoked — skip its "How to use / paste this" preamble. The issue report(s) are $ARGUMENTS below (plus any attached files — an error log, a screenshot description, the real project file the reader was working in). Read the guide's guide/ files yourself where you can.
  • You have file tools hereedit the guide on disk under guide/ (steps, status.md, decision-log.md, README.md, and a feedback-log.md entry for the report) as the prompt directs, rather than only printing fenced blocks.
  • Locate before you ask. Search the guide for the command, term, or symptom to place the issue yourself; only ask the reader a question when you genuinely can't place it or can't disambiguate two root causes.
  • When the prompt proposes a pedagogy rule (step 7), propose it and wait for approval before editing reference/pedagogy-rules.md — that file is repo-level, domain-agnostic content.
  • When the prompt hands off to audit-guide (step 9), use the sibling skill /audit-guide.

Issue report(s) / args:

$ARGUMENTS

Gate: run the prompt's Step 0 frontier gate first — read guide/foundation/progress.md, classify every edit the fix and its sweep would make, and if any load-bearing edit lands on a step already executed, stop and present the three routes before writing anything. The reader's failure is real — fix the guide, don't explain it away; fix the root cause everywhere it appears, not just where they hit it; never mark a rewritten milestone (the reader must re-run the Done-when gates); propose pedagogy rules, don't silently add them. Leave all changes in the working tree — do not commit.

Files

What ships with it

1 file 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. 2d ago First seen · 50 lines · 191 tokens per session scan A b35be161d4b5

Subscribe to this mod's changes

report-issue is a skill published in the GitHub repository tomthebearded/guide-forge (3 stars, last pushed 11d ago), licensed MIT. It adds 191 tokens to every session and 749 once invoked, about $0.0010 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.

Related

Other skills, from other repositories

writing

Draft, revise, audit, or transform human-facing prose: articles, blogs, documentation, criticism, essays, email, marketing and SEO copy, summaries, scripts, application materials, and UI text. Excludes code comments, commit messages, and private notes.

Anbeeld/WRITING.md · 54 tokens

renhua

Chinese public-writing editor for AI/tech posts, X/Twitter threads, product notes, and public technical essays. Use for 去AI味, 改得像本人, 写推特post, 精修中文AI技术文章 — removes AI-flavored shells while preserving facts, judgment, technical terms, and author voice. Not for academic papers, codebase docs, bid documents, or…

bahayonghang/my-ai-cli-toolkit · 87 tokens

document-writer

Write or update technical documentation grounded in the real codebase. Use when the user asks for README, API docs, architecture guides, user guides, CONTRIBUTING docs, migration notes, or JSDoc/code comments, or wants technical docs rewritten into natural Chinese with correct terminology. Not for general prose…

bahayonghang/my-ai-cli-toolkit · 75 tokens

Documentation Gap Finder

Audits a codebase or docs folder and lists everything that is undocumented, outdated, or unclear.

Notysoty/openagentskills · 24 tokens

Technical Blog Post Writer

Writes engaging, accurate technical blog posts targeted at developer audiences.

Notysoty/openagentskills · 17 tokens

technical-writing

Use when drafting or revising internal technical design docs, review notes, architecture writeups, or sharing posts in Chinese, especially when the tone should stay evidence-backed, calm, and suitable for peers or leaders rather than marketing or literary writing.

luoling8192/technical-writing · 51 tokens