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 skills add chrisgagne/grounded-forge --skill creating-corpusgit 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/creating-corpus)<a href="https://agentmods.dev/skills/chrisgagne/grounded-forge/creating-corpus"><img src="https://agentmods.dev/badge/skills/chrisgagne/grounded-forge/creating-corpus.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 5.1 | $0.00077 | $0.02570 |
| Opus 5 | $0.00039 | $0.01285 |
| Sonnet 5 | $0.00015 | $0.00514 |
| Haiku 4.5 | $0.00008 | $0.00257 |
Grade A, and why
creating-corpus 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 8d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creating Corpus
A corpus is the unit of self-contained material the matrix operates on: sources, references, distillations, lenses, builds, and packaged releases all live inside one folder. This skill scopes a new corpus—tier, domain, naming, task axes—and then invokes scripts/create-corpus.py to do the deterministic filesystem scaffold.
Dialogue skill, not a generator. The operator is in the conversation throughout. The skill produces scoping decisions captured in the corpus-level README.md; the script produces the directory tree.
When to use
- The operator is forking the repo and wants to start a new corpus for their own domain.
- The operator already has one corpus and wants to start a second under a different domain or scope.
- The operator is unsure whether the work belongs in
corpus.commons/orcorpus.local/and wants to talk through the tier decision before committing. - The operator has rough idea of what they want to read into a corpus but hasn't named the task axes yet.
When not to use
- The operator already has the scoping decisions made (corpus name, tier, task axes) and wants to skip the dialogue. Run
python scripts/create-corpus.py {target} --tasks t1,t2directly. - The operator wants to ingest a single source: that's
ingesting-resources, not this skill. - The operator wants to add a task axis to an existing corpus: that's
creating-tasks(scope the axis) pluscreating-applications(assemble the application), not this skill.
Inputs
- Optional: a rough corpus name or domain ("a coaching corpus", "management sciences", "anthropic-cookbook").
- Optional: existing related corpora; the new corpus might overlap with
corpus.commons/demo/or with an operator's existingcorpus.local/corpora.
Output
Three things, in order:
- Scoping decisions confirmed in the dialogue: tier, slug, task axes, scope range, intended first sources.
scripts/create-corpus.pyinvocation the operator runs (or the skill runs with operator confirmation): produces the corpus tree with stub indexes and a corpus-level README.- The corpus-level
README.mdwith the dialogue's scoping decisions captured: domain, owner, scope, licence, task axes, intended first sources.
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.
- 8d ago First seen · 135 lines · 0 tokens per session scan A c34777401c67
creating-corpus is a skill published in the GitHub repository chrisgagne/grounded-forge (7 stars, last pushed 17d ago), licensed MIT. It adds 77 tokens to every session and 2,570 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
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.
duckduckgo-search
Free keyless web, news, and image search via ddgs.
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
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.