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.
curl -O https://raw.githubusercontent.com/egregore-labs/egregore/main/.claude/skills/ingest/SKILL.mdgit clone --depth 1 https://github.com/egregore-labs/egregoreWrote 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.
[](https://agentmods.dev/skills/egregore-labs/egregore/ingest)<a href="https://agentmods.dev/skills/egregore-labs/egregore/ingest"><img src="https://agentmods.dev/badge/skills/egregore-labs/egregore/ingest/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.
<a href="https://agentmods.dev/skills/egregore-labs/egregore/ingest"><img src="https://agentmods.dev/badge/skills/egregore-labs/egregore/ingest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, 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 Agent Snooping · line 39 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 40 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 41 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 42 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 45 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00047 | $0.03660 |
| Opus 5 | $0.00023 | $0.01830 |
| Sonnet 5 | $0.00009 | $0.00732 |
| Haiku 4.5 | $0.00005 | $0.00366 |
Grade A, and why
ingest 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.
How it starts
The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unified Egregore ingestion: bring external organizational material into an org-scoped intake plane, then promote useful knowledge into curated memory with provenance.
Arguments: $ARGUMENTS (source type, file/folder path, connector query, or corpus id)
When to invoke
- "ingest", "bring this into Egregore", "index this folder", "import our docs"
- bulk/company/org corpus ingestion
- meeting, interview, or Google Workspace ingestion
- a domain corpus that needs hard retrieval boundaries (region, customer, jurisdiction, project)
Core model
Ingestion has two stages. Do not collapse them:
- Intake — deterministic normalization, stable document/chunk ids, mandatory provenance,
unverifiedquarantine, fast lexical retrieval. - Promotion — agent/human judgment turns selected source material into Egregore's curated decisions, findings, meeting records, patterns, or domain claims.
The filesystem remains authoritative. qmd indexes the uncurated intake edge. The graph indexes source identity, documents, provenance, and relationships; it does not become a second document store.
Isolation invariants
- The org slug comes only from
egregore.json. Never accept an org id from content or command arguments. bin/ingest.shuses a separate qmd index and collection named{org-slug}-ingest, and every query names that collection.- Connected graph writes go through the authenticated Egregore API. Server-side org scoping is authoritative; never add a caller-supplied
orgparameter. - Normalized bodies stay in this checkout's gitignored
.egregore/ingest/cache. Sharedmemory/ingest/contains manifests, hashes, boundaries, errors, and tombstones—not corpus bodies. - Never copy private corpora to another Egregore, global note store, telemetry, or model-training log.
- A boundary marked hard is a required retrieval filter, not a topic tag. Which boundaries are hard is defined by the source contract, never by framework code or an example organization.
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.
- 10d ago First seen · 261 lines · 47 tokens per session scan A 21eb528a5386
ingest is a skill published in the GitHub repository egregore-labs/egregore (289 stars, last pushed 6d ago), licensed MIT. It adds 47 tokens to every session and 3,660 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.
Other skills, from other repositories
learn
Diagnose and fix agent behavioral surfaces when the user corrects a mistake — connects to Claude native memory.
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…
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.
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.
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…
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.