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/finding-resourcesnpx skills add chrisgagne/grounded-forge --skill finding-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/finding-resources)<a href="https://agentmods.dev/skills/chrisgagne/grounded-forge/finding-resources"><img src="https://agentmods.dev/badge/skills/chrisgagne/grounded-forge/finding-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 | $0.00065 | $0.02939 |
| Opus 5 | $0.00032 | $0.01470 |
| Sonnet 5 | $0.00013 | $0.00588 |
| Haiku 4.5 | $0.00006 | $0.00294 |
Grade A, and why
finding-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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Finding Resources
Discovery and triage of candidate sources before paying the 9-pass ingestion cost. Each invocation produces a triage report at an operator-chosen path with three buckets:
- proceed: viable; ready to feed into
ingesting-resources - sample first: uncertain on one of the viability checks; one more probe needed
- skip: not viable, with the specific reason recorded
Viability rules in docs/architecture/source-integrity.md. Licence/scope distinction in the Distribution scope section of README.md and docs/architecture/copyright.md.
When to use
- Filling a thin distillation in an existing distillation index (e.g. the decision-making axis has no source on project management).
- Adding a new task axis (
creating-tasks→creating-applicationsworkflow): need candidate sources whose framing maps onto the new axis. - Forking the repo for a new corpus: step 2 of the README's forking flow ("Pick your sources") routes here.
- Auditing a candidate source someone has already named, when you want a structured viability check before committing to ingestion.
When not to use
- The source is already known and the operator wants to ingest it. Run
ingesting-resourcesdirectly. - The question is "is X already in our corpus?" Run
matching-references. - The question is "which existing reference applies to this situation?" Run
answer-from-corpus.
Setup
Inputs
The skill takes two flexible arguments.
Topic or gap query. Free-form ("project management for stakeholder engagement"; "rigorous group-decision-making research") or structured by axis + thin distillation ("decision-making axis, the conflict-resolution phase has no behavioural-science source"). The skill reads {corpus-root}/reference-index.json (file catalogue), {corpus-root}/concept-index.json (concept axis), and the relevant {corpus-root}/distillations/{task}/task-index.json to identify gaps and avoid recommending duplicates. The default {corpus-root} is corpus.commons/demo/ in this repo.
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 · 172 lines · 0 tokens per session scan A 1a85e4084b30
finding-resources is a skill published in the GitHub repository chrisgagne/grounded-forge (7 stars, last pushed 14d ago), licensed MIT. It adds 65 tokens to every session and 2,939 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 skills, from other repositories
warpp-workflow-authoring
Author WARPP workflows for Manifold as typed-port dataflow JSON. Use when a user asks to build, create, design, generate, or edit a Flow / workflow / automation / pipeline / DAG in Manifold, or mentions WARPP, workflow nodes, or the /flow builder. Covers the document format, port types and coercions, the builtin node…
manifold-api
Use when an agent needs to inspect or call the local Manifold HTTP API. Provides guidelines and scripts to filter specs before reading and handle payloads safely.
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
duckduckgo-search
Free keyless web, news, and image search via ddgs.
mcporter
List, auth, and call MCP servers/tools from the terminal.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.