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 skills/cogni-work/insight-wave/knowledge-ingest-sourcenpx skills add cogni-work/insight-wave --skill knowledge-ingest-sourcegit clone --depth 1 https://github.com/cogni-work/insight-waveWrote 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-source)<a href="https://agentmods.dev/skills/cogni-work/insight-wave/knowledge-ingest-source"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/knowledge-ingest-source.svg" alt="Measured on agentmods" 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 | $0.00174 | $0.06464 |
| Opus 5 | $0.00087 | $0.03232 |
| Sonnet 5 | $0.00035 | $0.01293 |
| Haiku 4.5 | $0.00017 | $0.00646 |
Grade A, and why
knowledge-ingest-source 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 today.
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 — 404 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Ingest — Single Source
The standalone single-source surface: deposit ONE source directly into the
bound wiki, with no research run (no knowledge-plan → knowledge-curate
→ knowledge-fetch scaffold, no fetch-manifest.json). A user drops one
input — a URL (web page or PDF), a local file (.docx/.html/.txt),
pasted text, a local PDF, or a local interview note — into their
bound base and it lands as a type: source page (or a type: interview page in
wiki/interviews/ for an interview note) carrying pre_extracted_claims:,
indexed and backlinked exactly like a research-ingested source. A URL stores
via fetch_method: webfetch; every local input stores honestly via
fetch_method: direct (the additive non-web method in fetch-cache.py's
VALID_FETCH_METHODS) — see Step 1 for why a local source is never stored as a
webfetch lie.
The mechanism reuses the research write path byte-for-byte: it populates
the shared fetch-cache, then dispatches the source-ingester agent (which reads
the cached body via fetch-cache.py fetch, dispatches claim-extractor, and
writes the page atomically with its Phase-3 pre-write integrity assertion),
then runs the same backlink_audit.py + wiki_index_update.py +
config_bump.py post-write lockstep knowledge-ingest Step 4 runs. The
source-ingester takes an additive PAGE_TYPE parameter (default source, so
a URL / file deposit is byte-identical to the research path; interview for a
local interview note → wiki/interviews/). The only single-source-specific
work is before the ingester: acquire the source body into the cache —
fetching a URL, or normalizing a local file (.docx/.html/.txt via the
vendored convert_to_md.py) / reading a local PDF (Read tool) / capturing
pasted text, all stored via fetch_method: direct — and dedup the source
against existing wiki pages so a collision routes to diff-before-write instead
of a blind overwrite.
Read ${CLAUDE_PLUGIN_ROOT}/references/inverted-pipeline.md §"Phase 4 —
knowledge-ingest" and references/claim-at-ingest.md once if you have not —
the claim-shape and write contracts are shared.
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.
- today Changed · +1 lines a78bbb7902e8
- 4d ago First seen · 403 lines · 174 tokens per session scan A ec8f1480b0cd
knowledge-ingest-source is a skill published in the GitHub repository cogni-work/insight-wave (12 stars, last pushed today), licensed Apache-2.0. It adds 174 tokens to every session and 6,464 once invoked, about $0.0009 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
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…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.