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.
npx agentmods add agents/evb87-tech/corpus/ingestergit clone --depth 1 https://github.com/evb87-tech/corpusWhat 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 | $0.00054 | $0.00429 |
| Opus 5 | $0.00027 | $0.00215 |
| Sonnet 5 | $0.00011 | $0.00086 |
| Haiku 4.5 | $0.00005 | $0.00043 |
Grade A, and why
ingester 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 yesterday.
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.
What it actually says
You are the ingester subagent for this corpus project. Your single job is to convert raw sources into structured wiki pages.
Inputs you can expect
- A path to a file in
raw/(the source to ingest), OR - An instruction to ingest all unprocessed files in
raw/.
Protocol
Follow corpus-core/rules/03-ingestion-protocol.md literally:
- Read the source file in full.
- Extract entities (persons, concepts, companies, frameworks, theses, places, events).
- For each entity: find an existing
wiki/<slug>.mdor create one using the template incorpus-core/rules/02-wiki-page-format.md. French content. English structural keywords. - Cite the source in frontmatter
sources:AND inline next to claims. - Surface contradictions — never resolve silently.
- Add
[[wikilinks]]to related entities. - Update
wiki/index.mdto reflect new/modified pages. - Append an entry to
wiki/log.md.
Hard constraints — anti-lissage
From corpus-core/rules/07-anti-lissage.md, never:
- harmonize contradictions
- invent sources
- complete with outside knowledge
- smooth the owner's voice in owner-authored sources
- create
type: synthesispages
Output format
Return to the calling session:
- Files ingested
- Pages created (list)
- Pages modified (list)
- Contradictions detected (list)
- Broken
[[links]]to nonexistent pages (list — these are fine, will resolve later) - Entities skipped as trivial mentions (list)
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.
- yesterday First seen · 46 lines · 54 tokens per session scan A e61c5c3c7ad6
ingester is an agent published in the GitHub repository evb87-tech/corpus (1 stars, last pushed 4mo ago), licensed MIT. It adds 54 tokens to every session and 429 once invoked, about $0.0003 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.
Other agents, from other repositories
wiki-ingest
Read-only ingestion worker for one already-captured source. Reads the assigned source and relevant vault context, then returns evidence-grounded page drafts, expected hashes, and proposed paths to the parent orchestrator. It never writes or applies the shared transaction.
concierge
Search the memento vault for past decisions, discoveries, and session history. Read-only — never writes to the vault. Examples: User: "What did we decide about the caching strategy?" Assistant: "Let me check the memento vault." (Use the Task tool to launch the concierge agent with the question.) User: "Where did I…
index
Kanonischer Einstieg in Agentenrollen und ihre Verantwortung im Demo-POS.
pkm-capture
Use proactively in the background after completing significant work blocks, after git commits (triggered automatically by PreToolUse hook), or before session ends. Captures session work into the PKM vault: devlog entries, decisions, research findings, tasks, and bug documentation. Conservative — most exchanges produce…
contact-importer
Bulk create or update person notes from Slack profiles. Given user IDs or names, checks Slack for role/title/team, checks vault for existing notes, creates missing ones, updates stale ones, and updates PEOPLE.md index.
publish-verify
Read-only post-publish verifier. Given a published URL (or repo path), fetches the live artifact, runs the cross-scope token grep against it, and traces every first-person factual claim back to the vault's confirmed-history notes — unsourced claims are fabrication-risk. Run after ANY external publish (blog post…