Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add cogni-work/insight-wave/plugin install cogni-knowledgeWrote 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/cogni-work/insight-wave/knowledge-ingest)<a href="https://agentmods.dev/skills/cogni-work/insight-wave/knowledge-ingest"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/knowledge-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/cogni-work/insight-wave/knowledge-ingest"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/knowledge-ingest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00140 | $0.13132 |
| Opus 5.5 | $0.00056 | $0.05253 |
| Sonnet 5.5 | $0.00028 | $0.02626 |
| Haiku 4.5 | $0.00014 | $0.01313 |
Grade A, and why
knowledge-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 1mo 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 — 466 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Ingest
Phase 4 of the inverted pipeline. Reads <project>/.metadata/fetch-manifest.json, dispatches source-ingester per fetched source to write wiki/sources/<slug>.md pages, and merges per-source results into the canonical <project>/.metadata/ingest-manifest.json. After per-source emission, a single first-party post-processing call (scripts/knowledge-ingest-postprocess.py, Step 4) applies the curated per-slug backlinks, indexes each source, and promotes each sub-question into a first-class type: question node at wiki/questions/<slug>.md whose ## Findings body [[links]] the source findings that answer it, backfilling the reverse source→question link (SCHEMA R1). Finally appends one ingest summary line to wiki/log.md.
By the end of this phase the wiki is populated with one type: source page per fetched[] entry, each carrying pre_extracted_claims: in its frontmatter. The composer reads these pages; verification string-matches draft sentences against the pre-extracted claims with zero network calls — the structural win.
Read ${CLAUDE_PLUGIN_ROOT}/references/inverted-pipeline.md §"Phase 4 — knowledge-ingest" and references/claim-at-ingest.md once to anchor on the contract.
When to run
fetch-manifest.jsonexists for the project (Phase 3 has run) AND eitheringest-manifest.jsondoes not yet exist OR the user explicitly wants to re-ingest.- User explicitly invokes
/cogni-knowledge:knowledge-ingest.
Never run when
- No
fetch-manifest.jsonexists at<project_path>/.metadata/— offerknowledge-fetchfirst. - No
binding.jsonexists at the resolved knowledge root — offerknowledge-setupfirst. binding.wiki_pathdoes not resolve to a directory containing.cogni-wiki/config.json— the binding is stale.
Parameters
| Parameter | Required | Description |
|---|---|---|
--knowledge-slug |
Yes | Slug of the bound knowledge base. |
--project-path |
Yes | Absolute path to the project directory. |
--knowledge-root |
No | Override the default knowledge-base directory. |
--batch-size |
No | Advisory cap on how many fetched sources one dispatch wave covers (a sub-batch of the full set). Ingesters in a wave fan out in a single message; Claude Code — not this cap — throttles actual concurrency. Default 25 (see references/fan-out-concurrency.md). |
--dry-run |
No | Print the dispatch plan (batch count, total sources, expected new pages) without running ingesters. |
--no-contradictor |
No | Skip the Step 4.6 ingest-time contradiction tripwire — including the Step 4.6.4 frontmatter persistence of recency-survivor resolutions. (--dry-run already skips it.) Default: the tripwire runs whenever a question group has a new source and at least one other claim-bearing page to compare it against. |
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.
- 1mo ago Changed · -6 lines 4c993fca6479
- 1mo ago First seen · 472 lines · 140 tokens per session scan A 33e943e733f4
knowledge-ingest is a skill published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 140 tokens to every session and 13,132 once invoked, about $0.0006 per session on Opus 5.5. 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
apify-youtube-transcript-scraper
Get YouTube captions, timestamped quotations, SRT/VTT and translated transcripts for videos, channels and playlists through the harshmaur/youtube-transcript-scraper Apify Actor.
legal-hold
Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.