egregore: Skill for Claude Code

.claude/skills/deep-reflect/SKILL.md

deep-reflect is a skill for Claude Code from egregore-labs/egregore. It costs 49 tokens per session (3,457 once invoked), scanned A, original, MIT.

A research skill that searches an organisation’s stored notes and documents across several linked steps, then produces a cited answer. It is for internal knowledge, not web research.

In plain words
What is it for?
Use it to research what the organisation knows, compare two ideas against its records, connect related findings, and identify claims that the documents do not support.
Why use it?
It helps answer questions that require connecting information scattered across many internal documents while showing where the conclusions came from.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions subagents; names the AskUserQuestion tool; mentions Codex.

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/telemetry.sh emit "command" '{"command":"deep-reflect","mode":"question","waves":3,"docs_read":24,"stop_reason":"saturated","duration_ms":210000}' 2>/d.

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/deep-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 deep-reflect

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/egregore-labs/egregore/deep-reflect"><img src="https://agentmods.dev/badge/skills/egregore-labs/egregore/deep-reflect.svg" alt="Reviewed on agentmods" width="80" 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 3,457 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: 1 finding, 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 106
    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 $0.00049 $0.03457
Opus 5 $0.00024 $0.01729
Sonnet 5 $0.00010 $0.00691
Haiku 4.5 $0.00005 $0.00346

Measured 10d ago against content hash 04e0b8c20c0e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

deep-reflect 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 10d 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/deep-reflect/SKILL.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deep research over org memory — ask a question, get a verified, cited synthesis of what the org collectively knows, including what it doesn't.

Multi-hop, multi-agent research over memory/ (plus the graph, when connected). Waves of parallel readers hop a lead ledger until saturation; a skeptic pass kills every claim it cannot re-find in the cited file. /reflect captures user thought; /deep-reflect researches what the org already knows.

Pipeline: deep-reflect v4 · 2026-07-11 · thin entry + sibling contracts (RESEARCH.md, ROLES.md, REPORT.md).

When to invoke

User says: "deep dive on X", "what do we know about X", "what does the knowledge base say about X", "research what we know about X", "what's the org's position on X", "cross-reference this", "analyze this against what we know", "connect the dots between X and Y" Not this: web sources → out of scope (this skill researches memory, not the web) · one-shot recall ("what did we decide about X") → /search · capture a new insight → /reflect · ask people, not documents → /harvest · private thought → /note · track the open question itself → /quest

Arguments: $ARGUMENTS (Optional: [question or insight] [--brief|--deep] [--quest ] [--no-capture] [--resume ])

Saves through the capture gate. A Save verdict runs the full /save flow — no separate /save after.

Modes

Mode Job Extra output
question (default) Answer a research question from memory
cross-ref v2's job: situate one insight against the corpus verified RELATES_TO/TENSION_WITH edge proposals (connected)

Both modes write reports to memory/knowledge/research/ — except --brief and probe-collapsed sparse runs, which default to terminal-only output with a two-option Save/Skip gate (Save writes the standard file). Depth bands are orthogonal; the default is dynamic, set by the Stage-0 corpus probe:

Band Waves Docs read Wall clock
--brief 1 ~8 ~1-2 min
standard ≤3 ~24 ~3-5 min
--deep ≤5 ~45 ~6-10 min

Read the full file on GitHub · 155 lines

Files

What ships with it

3 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. 10d ago First seen · 155 lines · 49 tokens per session scan A 04e0b8c20c0e

Subscribe to this mod's changes

deep-reflect is a skill published in the GitHub repository egregore-labs/egregore (289 stars, last pushed 6d ago), licensed MIT. It adds 49 tokens to every session and 3,457 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 2026-08-30.

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