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 commands/mnemehq/mneme/mneme-checkgit clone --depth 1 https://github.com/MnemeHQ/mnemeWrote 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/mnemehq/mneme/mneme-check)<a href="https://agentmods.dev/commands/mnemehq/mneme/mneme-check"><img src="https://agentmods.dev/badge/commands/mnemehq/mneme/mneme-check.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 | $0.00010 | $0.00206 |
| Opus 5 | $0.00005 | $0.00103 |
| Sonnet 5 | $0.00002 | $0.00041 |
| Haiku 4.5 | $0.00001 | $0.00021 |
Grade A, and why
mneme-check 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 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.
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.
This is a copy
100% identical to check — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Run mneme check against the current project memory.
If the user names a file, check that file's contents against
.mneme/project_memory.json. Otherwise, ask which file or scope.
Use the Bash tool:
mneme check \
--memory .mneme/project_memory.json \
--input <path> \
--query "<scope or task description>" \
--mode strict
Important: The --query argument controls which decisions are retrieved
for checking — it is not just a label. Use a descriptive phrase that matches
the scope of the change (e.g. "storage layer", "auth middleware") rather than
just the file name. Decisions are matched by keyword overlap between the query
and their scope, id, and text fields.
Report PASS / WARN / FAIL clearly. On FAIL, name the violated decision id and quote the anti-pattern or constraint that triggered it.
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 · 27 lines · 10 tokens per session scan A ea551c8b705f
mneme-check is a command published in the GitHub repository MnemeHQ/mneme (20 stars, last pushed today), licensed MIT. It adds 10 tokens to every session and 206 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to check, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
audit-duplication
Detect code duplication across crates and clients.
audit
Comprehensive code audit with per-crate reports via subagents.
review-plan-auto
Automated plan review-revise cycle (up to 4 rounds).
audit-crate
Audit a single crate (used by /audit coordinator or standalone).
review-plan
Review a plan/design doc as architect + staff developer.
differential-audit
Audit EARS↔code coherence via a bidirectional differential. With no arguments, opens a scoping conversation that interprets what the user wants audited, maps it to arrows, and captures an explicit EARS selection. With one or more EARS IDs, audits those specs directly using configured defaults. Requires docs/arrows/…