egregore: Skill for Claude Code

.claude/skills/reflect/SKILL.md

reflect is a skill for Claude Code from egregore-labs/egregore. It costs 52 tokens per session (6,212 once invoked), scanned A, original, MIT.

A guided way to record decisions, findings, and recurring patterns in shared project memory. It asks follow-up questions when deeper reflection is useful and saves the result automatically.

In plain words
What is it for?
Use it after making a decision, discovering a useful result, noticing a pattern, or wanting to preserve an insight for later work.
Why use it?
It prevents important conclusions from being lost in conversation or mixed with private, unfinished thoughts.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: names the AskUserQuestion tool; positional $N argument; mentions Claude Code.

This is egregore-labs/egregore's own configuration. It tells Claude Code how to work on egregore itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything egregore configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash bin/search.sh query "{artifact title / core claim}" --fast -n 3.

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/reflect/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.

agentmods badge for reflect

README.md
[![agentmods](https://agentmods.dev/badge/skills/egregore-labs/egregore/reflect/github.svg)](https://agentmods.dev/skills/egregore-labs/egregore/reflect)
Your own site
<a href="https://agentmods.dev/skills/egregore-labs/egregore/reflect"><img src="https://agentmods.dev/badge/skills/egregore-labs/egregore/reflect/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 reflect

Your own site · 80×15
<a href="https://agentmods.dev/skills/egregore-labs/egregore/reflect"><img src="https://agentmods.dev/badge/skills/egregore-labs/egregore/reflect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,212 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 high

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 →

  • high Anti-Refusal · line 501
    Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.
    Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
  • medium Excessive Agency · line 213
    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 $0.00052 $0.06212
Opus 5 $0.00026 $0.03106
Sonnet 5 $0.00010 $0.01242
Haiku 4.5 $0.00005 $0.00621

Measured 9d ago against content hash 2b34387ae2f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

reflect scanned grade A with 1 finding 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 9d 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.

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/reflect/SKILL.md · 666 lines

How it starts

The opening of the file, as written. The whole thing — 666 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Capture insights from your work — decisions, patterns, and realizations worth keeping.

The system uses graph context to surface what's worth reflecting on, asks Socratic follow-ups, and auto-classifies what emerges.

When to invoke

User says: "we decided", "I realized", "I keep noticing", "capture this insight", "that's a pattern", "important takeaway", "let me record this" Not this: thought is half-baked/private → /note · want deep cross-referencing → /deep-reflect · insight is about AI steering → /archive

Topic: $ARGUMENTS

Auto-saves. No need to run /save after.

Three Modes

Invocation Mode AskUserQuestion calls
/reflect Deep — full Socratic flow 2-3
/reflect [content] Quick — rapid capture, auto-classify 0-1
/reflect about [topic] Focused — deep but pre-seeded 1-2

Mode detection:

  • No arguments → Deep mode
  • Arguments start with about → Focused mode (topic = everything after "about ")
  • Arguments match [category]: [content] (decision/finding/pattern prefix) → Quick mode with category override
  • Any other arguments → Quick mode

Mode detection

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

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

Local-mode flow:

  • Step 0: Get user via git config user.name. Skip ALL context queries (Q1-Q6) entirely — do not run them.
  • Step 1 (Deep/Focused): Ask opening question based on conversation context only (no graph-aware opening, no opportunity detection from queries). Use what you know from the current session.
  • Step 2: Same deepening flow, based on conversation context.
  • Step 3: Same auto-classification.
  • Step 4: Skip relation detection entirely — do not run quest/artifact queries.
  • Step 5: Create files — same as connected mode.
  • Step 6: Skip entirely — no Neo4j Artifact creation.
  • Step 7: Auto-save — same as connected mode.
  • Step 8: TUI — use ✓ Saved · pushed (not "graphed"). Use Visible in /activity. as footer.

Read the full file on GitHub · 666 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.

  1. 9d ago First seen · 666 lines · 52 tokens per session scan A 2b34387ae2f4

Subscribe to this mod's changes

reflect is a skill published in the GitHub repository egregore-labs/egregore (282 stars, last pushed 5d ago), licensed MIT. It adds 52 tokens to every session and 6,212 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

learn

Diagnose and fix agent behavioral surfaces when the user corrects a mistake — connects to Claude native memory.

automagik-dev/genie · 23 tokens

memorywhale

Query and write durable debugging memory recorded by MemoryWhale. Use when debugging a failure that may have happened before, when you need the exact error/flags/output from an earlier attempt, when the user asks "how did we fix this last time?", or once you've figured out why something failed / how a fix worked and…

wuisabel-gif/MemWhale · 79 tokens

init

Turn on Rekal memory in the current repository by running rekal init. Use when the user asks to initialize or set up Rekal here, or when a rekal command reported the repository is not initialized. Once per repository. Do not offer this merely because a repo lacks a .rekal/ store — most repos do not want one.

rekal-dev/rekal-cli · 75 tokens

install

Install the Rekal binary on this machine. Use when rekal is not on PATH — a command reported command not found — or when the user asks to install Rekal. Once per machine, not per repository; to set up a repo that already has the binary, use the init skill instead.

rekal-dev/rekal-cli · 66 tokens

atomic-wiki

Conversational wiki and capture-bucket routing. Fires when the user wants a place, space, or folder for notes, research, tickets, raw dumps, or knowledge capture — checks the block in /.claude/CLAUDE.md; if the cwd is under a registered realm, creates the folder as a bucket via atomic wiki bucket add rather than a…

damusix/atomic-claude · 204 tokens

remem

Use when the user asks Codex to recall prior project context, save durable decisions or bug fixes, inspect remem memory health, or activate remem automatic memory hooks from the Codex plugin.

majiayu000/remem · 42 tokens