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 agentmods add skills/sofiahernandes/margaret/margaret-helpnpx skills add sofiahernandes/margaret --skill margaret-helpgit clone --depth 1 https://github.com/sofiahernandes/margaretWrote 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/sofiahernandes/margaret/margaret-help)<a href="https://agentmods.dev/skills/sofiahernandes/margaret/margaret-help"><img src="https://agentmods.dev/badge/skills/sofiahernandes/margaret/margaret-help.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 | $0.00056 | $0.01024 |
| Opus 5 | $0.00028 | $0.00512 |
| Sonnet 5 | $0.00011 | $0.00205 |
| Haiku 4.5 | $0.00006 | $0.00102 |
Grade B, and why
margaret-help scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Displays the current level (`[MARGARET]`, `[MARGARET:MAX]`). Not wired in automatically — add this to `~/.claude/settings.json`: How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Margaret Help
Show this card on invocation. It's a one-shot display — don't switch modes, write state files, or persist anything as a side effect.
Supported hosts
Full command/skill/hook support: Claude Code (.claude-plugin/), Codex (.codex-plugin/, shares hooks/claude-hooks.json). Context-file only, no hook system or mode switching: Gemini CLI (gemini-extension.json → AGENTS.md), Cursor (.cursor/rules/margaret.mdc), Windsurf (.windsurf/rules/margaret.md), Cline (.clinerules/margaret.md) — on these three the screen applies unconditionally, since there's no hook layer to drive /margaret lean|full|max. Copilot/Qoder ship reference hook manifests only (hooks/copilot-hooks.json, hooks/qoder-hooks.json) for manual wiring into that tool's own settings — no packaged install for either.
Commands
| Command | Args (default) | What it does |
|---|---|---|
/margaret |
lean|full|max|off (full) |
Senior-engineer persona: requirement check → reuse → stdlib → platform → dependency → one line → minimal build. Holds until changed or session end. |
/margaret-scan |
[repo] (diff) |
One-shot over-engineering scan: L42: overbuilt: factory, one product. Inline. repo widens the scan to the whole tree instead of just the diff. |
/margaret-review |
— | Switches the session persona to review mode: same complexity-hunt framing as /margaret-scan, but holds across turns and propagates into subagents like /margaret lean|full|max — not a one-shot pass. Hidden mode, not its own skill; revert with /margaret full or "stop margaret". |
/margaret-guard |
— | Security pass on the current diff: exploitable findings only, false positives filtered out. |
/margaret-design |
design|diagram|code|context|connect|motion (design) |
Figma bridge both ways: generate a new artifact or pull an existing file/selection into code. |
/margaret-help |
— | This card. |
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.
- 5d ago First seen · 77 lines · 56 tokens per session scan B 07c82f4b92ad
margaret-help is a skill published in the GitHub repository sofiahernandes/margaret (2 stars, last pushed 21d ago), licensed MIT. It adds 56 tokens to every session and 1,024 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
chatcrystal-debug-recall
Recall ChatCrystal memories for debugging tasks involving failing tests, compiler errors, runtime exceptions, dependency issues, environment breakage, or performance regressions. Use when historical root causes, fixes, or pitfalls may accelerate diagnosis before proposing a fix.
test-coverage
Use after writing tests to assess coverage quality across structural, mutation, requirements, and API/integration dimensions; organized knowledge for choosing and interpreting coverage analyses.
tmux-ui-tripwire
Write or debug tmux-driven end-to-end TUI tests ("tripwires") for the ainb terminal app. Use when the user asks to "write a tmux test", "add a tripwire", "verify the TUI in tmux", "test feature X by pressing key Y", "validate plugin Z renders", or when editing any file under crates/ainb-core/tests/tripwire.rs.…
do-competitively
Execute tasks through competitive multi-agent generation, meta-judge evaluation specification, multi-judge evaluation, and evidence-based synthesis.
verify
Fact-check claims encountered during reading — dates, names, events, citations. Use when encountering historical facts or disputed claims.
create-rule
Use when found gap or repetative issue, that produced by you or implemenataion agent. Esentially use it each time when you say "You absolutly right, I should have done it differently." -> need create rule for this issue so it not appears again.