An issue-reporting workflow that captures the surrounding context and sends a software problem to the appropriate place. It is meant for bugs and broken commands, rather than personal to-do items or open-ended team research.

Reporting broken features, commands, or other software problems, with optional attachment of a conversation transcript.

It gives reported problems a consistent record and routing process, so bugs are less likely to be forgotten or mixed with unrelated work.

How egregore-labs/egregore configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to egregore-labs/egregore. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/egregore-labs/egregore/main/.claude/skills/issue/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/egregore-labs/egregore

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/egregore-labs/egregore/issue.svg)](https://agentmods.dev/skills/egregore-labs/egregore/issue)

Your own site

<a href="https://agentmods.dev/skills/egregore-labs/egregore/issue"><img src="https://agentmods.dev/badge/skills/egregore-labs/egregore/issue.svg" alt="Measured on agentmods" height="20"></a>

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 8,400 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00049	$0.08400
Opus 5	$0.00024	$0.04200
Sonnet 5	$0.00010	$0.01680
Haiku 4.5	$0.00005	$0.00840

Measured 8d ago against content hash 32a17b9ad0e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade C, and why

issue scanned grade C with 2 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 8d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf "$staging_dir"

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**Neo4j-first.** All queries via `bash bin/graph.sh query "..."`. No MCP. No direct curl to Neo4j.

.claude/skills/issue/SKILL.md · 874 lines

How it starts

The opening of the file, as written. The whole thing — 874 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Report an issue. Captures context and routes to the right place.

When to invoke

User says: "this is broken", "bug in", "something's wrong with", "file an issue", "report a problem", "[command] isn't working" Not this: personal task → /todo · team exploration → /quest

Topic: $ARGUMENTS

Auto-saves. No need to run /save after (create mode only).

Mode detection

MODE=$(jq -r '.mode // "connected"' egregore.json 2>/dev/null)

Local mode (mode === "local"): Skip ALL bin/graph.sh and bin/notify.sh calls — do NOT run them. Do NOT show any graph-related messaging ("Graph offline", "will sync", Neo4j, etc.).

Local-mode flow:

Create mode: Step 0 context capture — run Bash call 1 (git identity + state) normally; skip Bash call 2's bin/graph.sh test line (keep the memory-symlink and egregore.json checks); skip the Neo4j recent-session query entirely. Steps 1-2 (description, smart routing) work normally. Step 3 — write the markdown file to memory/knowledge/issues/ normally, but skip the Neo4j CREATE (i:Issue) node and the progress message referencing "graph". Step 4 transcript attachment works normally when --transcript is present. Step 5 — skip graph routing updates (Neo4j node creation, relationship updates), but preserve gh issue create if the smart routing targets a GitHub repo (GitHub CLI is independent of the graph). Skip Step 6 notifications entirely. Steps 7-8 (auto-save, confirmation TUI) work normally — in the TUI, show ✓ Saved to memory (omit "graphed" and "team notified").
List mode: Read issues from memory/knowledge/issues/ directory — derive id from filename (e.g., 2026-03-30-memory-bug.md → memory-bug), parse frontmatter for title, status, recipient, date (display as created), topics, author (display as reportedBy). Render same TUI.
Close mode: Find issue file in memory/knowledge/issues/, update frontmatter status: closed + add closed: {date}. Skip graph update. If frontmatter has github_url, still run gh issue close "{github_url}" 2>/dev/null — GitHub CLI is independent of the graph.
Search mode: Grep through memory/knowledge/issues/ files for matching text. Render same TUI.
Notifications: Skip entirely — do not mention notifications.

Read the full file on GitHub · 874 lines

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.

8d ago First seen · 874 lines · 49 tokens per session scan C 32a17b9ad0e8

Subscribe to this mod's changes

issue is a skill published in the GitHub repository egregore-labs/egregore (282 stars, last pushed 4d ago), licensed MIT. It adds 49 tokens to every session and 8,400 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code Collaboration Debugging ai claude cli developer-tools

printing-press-polish

Polish a generated CLI to pass verification and become publish-ready. Runs diagnostics (dogfood, verify, scorecard, go vet, gosec), automatically fixes all issues (verify failures, static-analysis findings, dead code, descriptions, README, MCP tool quality), reports the before/after delta, and offers to publish. Use…

mvanhorn/cli-printing-press · 125 tokens

printing-press-amend

Amend a published CLI from one of two input sources: (1) dogfood mode mines the active Claude Code session transcript for friction (missing flags, hand- rolled API payloads, silent-null returns); (2) direct-input mode accepts user-supplied asks (rename a command, add commands or feeds, fix a named bug, optionally…

mvanhorn/cli-printing-press · 222 tokens

printing-press-output-review

Internal sub-skill: agentic review of a printed CLI's sampled command output for plausibility issues that rule-based checks can't encode (substring-match relevance, format bugs, silent source drops, ranking failures). Invoked via the Skill tool by the main printing-press skill at Phase 4.85 and printing-press-polish…

mvanhorn/cli-printing-press · 102 tokens

egregore: Skill for Claude Code