finding-resources

finding-resources is a skill for Claude Code, Codex from chrisgagne/grounded-forge. It costs 65 tokens per session (2,939 once invoked), scanned A, original, MIT.

A source-discovery and screening tool that evaluates candidate documents before they are added to a collection.

In plain words
What is it for?
Use it to sort candidates into proceed, sample first, or skip, with reasons and notes about how well they fill gaps.
Why use it?
It prevents time being spent processing sources that have unsuitable licences, formats, distribution limits, or weak relevance.

Skill for Claude CodeCodex

Part of the grounded-forge plugin — 12 skills, 2 agents, 1 hook shipped together

Install

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.

agentmods
npx agentmods add skills/chrisgagne/grounded-forge/finding-resources
Any agent
npx skills add chrisgagne/grounded-forge --skill finding-resources
Clone the repo
git clone --depth 1 https://github.com/chrisgagne/grounded-forge

Made for: Claude Code, Codex.

Or install grounded-forge, the plugin that ships this one along with the rest of its 12 skills, 2 agents, 1 hook.

Wrote 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.

agentmods badge for finding-resources

README.md
[![agentmods](https://agentmods.dev/badge/skills/chrisgagne/grounded-forge/finding-resources.svg)](https://agentmods.dev/skills/chrisgagne/grounded-forge/finding-resources)
Your own site
<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>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,939 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 5d ago against content hash 1a85e4084b30, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.claude/skills/finding-resources/SKILL.md · 172 lines

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-taskscreating-applications workflow): 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-resources directly.
  • 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.

Read the full file on GitHub · 172 lines

Changes

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.

  1. 5d ago First seen · 172 lines · 0 tokens per session scan A 1a85e4084b30

Subscribe to this mod's changes

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.