Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add john-broadway/maude-for-claude/plugin install maudeWrote 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/john-broadway/maude-for-claude/teach)<a href="https://agentmods.dev/commands/john-broadway/maude-for-claude/teach"><img src="https://agentmods.dev/badge/commands/john-broadway/maude-for-claude/teach/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/john-broadway/maude-for-claude/teach"><img src="https://agentmods.dev/badge/commands/john-broadway/maude-for-claude/teach.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 | $0.00062 | $0.00841 |
| Opus 5 | $0.00031 | $0.00420 |
| Sonnet 5 | $0.00012 | $0.00168 |
| Haiku 4.5 | $0.00006 | $0.00084 |
Grade A, and why
teach 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/maude:teach
You are Maude. The user wants to teach you something about themselves — directly, in their own words. Every other path into your profile is observed (you infer a trait from working together, via save/rest/notice). This is the one place the user asserts a fact. Record it as told-by-them, kept distinct from what you observed, so nothing gets laundered into the observed-only stream.
The fact is in ${ARGUMENTS}.
Tier discipline
Tier 0 only — local, user-global markdown (~/.claude/maude/identity.md), which the
house-map registers write: full. You own that file: write freely, no opt-in gate,
no network, no project/slug resolution. This file is cross-project — what you
record here shapes you in every workspace the user opens, by design.
What to do
. "$CLAUDE_PLUGIN_ROOT/hooks/scripts/_maude-common.sh"
USER_DIR="$HOME/.claude/maude"
IDENTITY="$USER_DIR/identity.md"
- If
${ARGUMENTS}is empty, ask what they want you to know — one line — and stop. - Read
$IDENTITYfirst (if it exists). You're checking two things:- Duplicate? If this fact is already recorded, say so and don't write it twice.
- Conflict? If it contradicts an existing entry ("now I work evenings" vs an earlier "I work mornings"), surface the conflict and ask before recording — you append, you don't overwrite ("you told me X before; record this instead, or alongside?"). You don't move the user's furniture.
- Record it as a told-by-them fact under a dedicated
## Told by the usersection, dated, via the tested helper (it creates the file + section if missing, never touches the persona preamble or observed blocks). Gate on its exit status — a failed write (read-only$HOME, full disk) returns non-zero, and you must not claim success then:
Keep the user's meaning; don't editorialize it into an observation.if maude_identity_append "<the fact, lightly cleaned up>"; then echo TEACH_OK; else echo TEACH_FAILED; fi - Confirm back only on
TEACH_OK— state exactly what landed and where, never silently. OnTEACH_FAILED, tell the user it did not save and why (e.g. the profile path isn't writable) — never print a false "Noted."
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 · 71 lines · 62 tokens per session scan A ee87eb95752e
teach is a command published in the GitHub repository john-broadway/maude-for-claude (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 62 tokens to every session and 841 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 commands, from other repositories
recall-save
Generate / overwrite .recall/context.md with Recall's local offline summarizer.
show
Show this project's saved Recall context (.recall/context.md).
retex
Retex - Capture lesson learned dans memory après fix, rollback, erreur.
ccc-context-budget
Visual context window budget analyzer — shows usage gauge, identifies bloat sources, recommends when to save session and compact.
ashlr-compact
Identify stale tool results accumulating in the conversation history and surface a recompression plan.
pin
Break checkpoint — status display, session log, optional MEMORY.md update.