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/chrisgagne/grounded-forge/ingesting-resourcesnpx skills add chrisgagne/grounded-forge --skill ingesting-resourcesgit clone --depth 1 https://github.com/chrisgagne/grounded-forgeWrote 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/chrisgagne/grounded-forge/ingesting-resources)<a href="https://agentmods.dev/skills/chrisgagne/grounded-forge/ingesting-resources"><img src="https://agentmods.dev/badge/skills/chrisgagne/grounded-forge/ingesting-resources.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 | $0.00076 | $0.05250 |
| Opus 5 | $0.00038 | $0.02625 |
| Sonnet 5 | $0.00015 | $0.01050 |
| Haiku 4.5 | $0.00008 | $0.00525 |
Grade A, and why
ingesting-resources 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 5d 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 — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ingesting Resources
Promotes a source from {corpus-root}/sources/ingest/ (staging) to {corpus-root}/sources/original/ (audited) by running the 9-pass protocol against it.
Each successful invocation produces, all inside the active corpus:
- One sidecar at
sources/original/{slug}.source.mdwith frontmatter (title, author, URL, scope, licence, ingested, original_format, checksum_sha256). - Converted markdown at
sources/converted/{slug}.md(the "tape" Pass C read). - One deep reference at
references/{slug}-deep.md. - One light reference at
references/{slug}.md. - One distillation per applicable task axis at
distillations/{task}/{slug}-{task}.md. The protocol forms an opinion about applicability and asks the operator to confirm borderline cases. - Updates to the runtime JSON indexes (
references/slug-table.json,reference-index.json,concept-index.json, per-taskdistillations/{task}/task-index.json) and the operator-inspection.mdviews alongside. - Substantive images extracted and indexed in
{corpus-root}/sources/converted/IMAGE-INDEX.yaml. - An ingestion summary.
- The input source removed from
sources/ingest/. Directory state is the workflow indicator: anything iningest/is unaudited; anything inoriginal/has been through the protocol.
{corpus-root} is operator-supplied (e.g., corpus.commons/demo/). Default: active corpus from working-directory inference, or builds.yaml's defaults.source_dir.
Per-pass procedures, templates, and failure modes are in 9-pass-protocol.md.
When to use
- Adding a new source to the corpus.
- Re-ingesting after a substantive revision (new edition, corrected text, previous Pass I failure).
- Re-ingesting when a model advance makes the deep ref materially better.
When not to use
- Editing an existing reference's prose. Substantive edits rerun Pass C onwards; cosmetic edits rerun Pass I at minimum.
- Adding a new task axis without a new source. Run
creating-tasks→creating-applicationsinstead. - Searching the corpus for an existing source. Run
matching-referencesinstead.
What ships with it
1 file 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.
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.
- 5d ago First seen · 271 lines · 76 tokens per session scan A f37e4d637eac
ingesting-resources is a skill published in the GitHub repository chrisgagne/grounded-forge (7 stars, last pushed 14d ago), licensed MIT. It adds 76 tokens to every session and 5,250 once invoked, about $0.0004 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 skills, from other repositories
dcf-model
Build discounted cash flow valuation workbooks in Excel.
comps-analysis
Build comparable-company valuation workbooks in Excel.
siyuan
Query and edit a SiYuan knowledge base via its API.
xlsx
Create, read, edit Excel .xlsx workbooks and CSVs.
excel-author
Build auditable financial workbooks headless via openpyxl.
pptx-author
Build PowerPoint decks headless with python-pptx.