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.
git clone --depth 1 https://github.com/tacoda/keystoneWrote 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/commands/tacoda/keystone/learn)<a href="https://agentmods.dev/commands/tacoda/keystone/learn"><img src="https://agentmods.dev/badge/commands/tacoda/keystone/learn/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/commands/tacoda/keystone/learn"><img src="https://agentmods.dev/badge/commands/tacoda/keystone/learn.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 | $0.00016 | $0.00555 |
| Opus 5.5 | $0.00006 | $0.00222 |
| Sonnet 5.5 | $0.00003 | $0.00111 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade A, and why
learn 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- keystone-learn — 97% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
learn
Capture a learning candidate from a surprise, an incident, or a review finding. Writes to .charter/learning/inbox/ for later synthesis. Read .charter/learning/README.md.
Activities
Write a candidate to .charter/learning/inbox/<timestamp>-<slug>.md where:
<timestamp>isYYYY-MM-DD-HHMMin UTC<slug>is a short kebab-case description of the insight
The candidate file uses this shape:
---
captured: <ISO date>
source: <what triggered this — review finding, surprise during implementation, etc.>
proposed-layer: <corpus/principles | guides/idioms/<stack> | guides/process | sensor>
proposed-globs: # optional; see below
- "src/billing/**"
- "tests/billing/**"
---
## What happened
<concrete observation — code, output, or interaction>
## Why it matters
<the principle, idiom, or rule this implies>
## Proposed change
<the smallest charter edit that would prevent the next incident>
proposed-globs: — record the paths the lesson came from
When the surprise happened in a specific region of the codebase, list the paths in proposed-globs:. These are the touched files (or their parent directories' globs) from the interaction that produced the candidate. Synthesize uses this as signal when deciding the guide's actual globs:.
- If the lesson is cross-cutting (would apply to any file in any stack), omit the field. Synthesize will default to no
globs:on the promoted guide. - If the lesson is regional, list the patterns that match the affected files. Prefer existing region globs from
corpus/state/CODEBASE_STATE.mdover hand-invented patterns — globs should reflect the real codebase, not the abstraction the rule is about. - Never set
proposed-globs:wider than where the surprise actually occurred. Synthesize narrows on user confirmation; widening at learn-time loses the evidence.
Gate
Learn writes only to the inbox. Promotion into corpus / guides happens in synthesize, not here. Capture liberally; prune aggressively later.
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.
- 1mo ago First seen · 57 lines · 16 tokens per session scan A 1730469b6500
learn is a command published in the GitHub repository tacoda/keystone (44 stars, last pushed 3mo ago), licensed MIT. It adds 16 tokens to every session and 555 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
train-executor
Generate an executor onboarding playbook from a person's Freedom Path DELEGATE bucket. Produces SOPs in the person's voice, a training curriculum, and outdated-material flags. Non-technical-friendly — designed for Claude Desktop + Cowork usage.
training-coach-trainer
Train-the-trainer (TtT) protocol for internal subject-matter-experts who will deliver a training program. Condensed adult-learning principles, facilitation skills, common SME-as-trainer failure modes, cohort facilitation practice schedule, and a TtT-readiness rubric. Refuses SME deployment without TtT.
training-curriculum
Outcome-back curriculum design for a single program or module. Starts from the L3 job behavior change and L4 business outcome; works backward through capability requirements, sequencing, spaced retrieval, cognitive-load chunking, encoding-context simulation, and per-module evaluation rubric. Refuses content-first…
training-measure-transfer
Kirkpatrick L3 (behavior) + L4 (results) measurement plan for a training program. Behavior observation protocol with sampling cadence, business-metric tracking, post-program reinforcement plan, redesign feedback loop. Refuses L1-only smile-sheet evaluation; refuses programs without baseline.
training-program-design
Full program architecture for a multi-week or multi-month training program. Wraps a Curriculum Design with cadence (synchronous + asynchronous + on-job), trainer brief, learner journey, manager-engagement plan (mandatory — without manager reinforcement, transfer evaporates), measurement plan, and ROI projection.…
training-scenarios
Scenario / case library design for a skill domain — 10-15 scenarios across difficulty range with setup, decision points, response rubric, and debrief discussion guide. Format mirrors the structured-interview rubric pattern from the Hiring sub-system. Scenarios are the bridge from concept to on-job behavior; without…