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 advise-from-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/advise-from-corpus)<a href="https://agentmods.dev/skills/chrisgagne/grounded-forge/advise-from-corpus"><img src="https://agentmods.dev/badge/skills/chrisgagne/grounded-forge/advise-from-corpus/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/chrisgagne/grounded-forge/advise-from-corpus"><img src="https://agentmods.dev/badge/skills/chrisgagne/grounded-forge/advise-from-corpus.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00167 | $0.04963 |
| Opus 5.5 | $0.00067 | $0.01985 |
| Sonnet 5.5 | $0.00033 | $0.00993 |
| Haiku 4.5 | $0.00017 | $0.00496 |
Grade A, and why
advise-from-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 19d 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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Advise from corpus
answer-from-corpus answers the question as asked. This skill checks the question first. Its canonical case:
"How do I improve my user stories? I hear to write them vertically?"
A good answer about vertical slicing is useless to someone whose teams are split into a front-end team and a back-end team, each with its own backlog, because no team can finish a vertical slice. The advice this person needs starts with a question back: can one of your teams take a story from interface to database to done?
The skill does three things in order:
- Frame. It reads the question for what it assumes and names the constraint: the one fact that, if it went the other way, would change the advice most. It asks grounded framing questions and reads each reply as evidence, asking again in a new form when a reply leaves the constraint open, until it knows that fact or the user opts out.
- Answer. It hands retrieval to
answer-from-corpus, with what the framing established. - Teach back. It names the check it ran and where it came from, so the user can ask it themselves next time.
It never holds the answer hostage. A user who says "just answer" gets the answer, stated with the condition under which it holds.
Procedure
Retrieval belongs to answer-from-corpus. Every read in this skill (framing sources, the answer) follows that skill's run mode, lens check, protocols, quote checking and grounding discipline. In the project it routes through the concept index to references. In an app it reads the distillations the app ships. This skill adds the framing conversation and the teach-back, and doesn't restate the retrieval rules.
Step 1: Decide whether to frame
Classify the query shape the way answer-from-corpus does. Then:
- Named lookup ("what does the Scrum Guide say about the Sprint Goal"): don't frame. Run
answer-from-corpusand stop. - The user asks for the answer only ("just answer", "no questions"): don't ask. Run the framing read in Step 2, answer with the condition of validity from Step 5, and skip the questions.
- A crisis still unfolding ("prod is down", "we're losing the account today"): don't frame. Act first; offer framing once things are stable.
- Everything else, diagnostic or synthesis: frame. The framing read runs whether or not a lens applies.
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.
- 19d ago Changed · +59 lines · +25 tokens per session 8ff01cc57f13
- 27d ago First seen · 173 lines · 142 tokens per session scan A d93be44e92d0
advise-from-corpus is a skill published in the GitHub repository chrisgagne/grounded-forge (8 stars, last pushed yesterday), licensed MIT. It adds 167 tokens to every session and 4,963 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-09-27.
Other skills, from other repositories
learn
Use this skill when the user wants intellectual understanding — learning how or why something works, not getting a task done or soliciting Claude's judgment. Trigger for: Explicit learning requests: teach, explain, ELI5, walk me through, quiz me, flashcards, "I'm rusty on"; definitions ("what is X") Terse concept…
mem0-vercel-ai-sdk
Mem0 provider for Vercel AI SDK (@mem0/vercel-ai-provider). TRIGGER when: user mentions "vercel ai sdk", "@mem0/vercel-ai-provider", "createMem0", "retrieveMemories", "addMemories", "getMemories", "searchMemories", "mem0 vercel", "AI SDK provider", "AI SDK memory", or is using generateText/streamText with mem0. Also…
mem0-tour
Browses all stored memories grouped by category with full content display. Use when reviewing all project memories, exploring stored knowledge, onboarding to a project, or getting an overview of captured decisions, conventions, and learnings.
ai-engineering-toolkit
Overview of six AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
status
Show whether Mem0 memory is working in this repository, covering configuration, capture state, pending flushes, and whether the Mem0 API key is valid. Use when the user asks whether memory is on, why a memory is missing, or anything looks broken.
pause
Pause Mem0 memory capture on this machine. Use when the user wants to stop memories being recorded, for example for private work or experiments.