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 n24q02m/mnemo-mcp --skill knowledge-auditgit clone --depth 1 https://github.com/n24q02m/mnemo-mcpWrote 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/n24q02m/mnemo-mcp/knowledge-audit)<a href="https://agentmods.dev/skills/n24q02m/mnemo-mcp/knowledge-audit"><img src="https://agentmods.dev/badge/skills/n24q02m/mnemo-mcp/knowledge-audit.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 5.1 | $0.00021 | $0.01494 |
| Opus 5 | $0.00010 | $0.00747 |
| Sonnet 5 | $0.00004 | $0.00299 |
| Haiku 4.5 | $0.00002 | $0.00149 |
Grade A, and why
knowledge-audit 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 7d 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
2 near-identical copies found in the catalogue:
- knowledge-audit — 100% identical, 0 lines differ
- knowledge-audit — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Audit
Systematic review of stored memories to maintain quality. Finds duplicates, detects contradictions, flags stale entries, and consolidates overlapping memories.
Steps
-
Scope the audit:
- If topic specified:
memory(action="search", query="[topic]")to find all related memories - If "all":
memory(action="list")to get full inventory, thenmemory(action="stats")for overview - Group memories by tag/category for systematic review
- If topic specified:
-
Identify duplicates:
- Search for memories with similar content or overlapping keywords
- Compare pairs that cover the same topic
- Decision: keep the more detailed/recent one, delete the other
- Use
memory(action="delete", id="[duplicate-id]")for removals
-
Detect contradictions:
- Look for memories that make opposing claims about the same topic
- Examples: "Use library A" vs "Switched to library B", conflicting conventions
- Decision tree:
- Both have dates -> keep the newer one (it supersedes)
- Neither has date -> ask user which is current
- Both are valid (context-dependent) -> update both to clarify their scope
- Update the surviving memory to note it supersedes the old one
-
Flag stale entries:
- Memories referencing specific versions that are now outdated
- Memories about temporary workarounds that may have been resolved
- Memories about tools/libraries that have been replaced
- Action: mark as stale with
memory(action="update", ...)adding[STALE]prefix, or delete if clearly obsolete
-
Consolidate overlapping memories:
- Multiple memories about the same topic that each have partial info
- Merge into a single comprehensive memory
- Steps: create new consolidated memory -> verify retrieval -> delete originals
- Use
memory(action="consolidate", ...)if available, otherwise manual merge
-
Produce audit report:
## Knowledge Audit — [topic/all] — [date] ### Summary - Total memories reviewed: [N] - Duplicates removed: [N] - Contradictions resolved: [N] - Stale entries flagged/removed: [N] - Memories consolidated: [N merged into M] ### Actions Taken - [list of specific changes] ### Recommendations - [any patterns noticed, e.g., "many memories lack WHY context"]
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.
- 7d ago First seen · 143 lines · 21 tokens per session scan A 6e0224fe7810
knowledge-audit is a skill published in the GitHub repository n24q02m/mnemo-mcp (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 21 tokens to every session and 1,494 once invoked, about $0.0001 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 skills, from other repositories
scrape-batch
Extract many known URLs in one polite, rate-limited pass. Use when the user hands over a list of links, a set of search hits to read in full, or asks to "scrape these pages" / "pull the content from all of them". Drives extract(action="batch"), which fans out with per-domain rate limiting and returns partial results…
compare
Structured comparison of 2+ alternatives with consistent criteria and decision matrix.
research-topic
Multi-step research orchestration. Use when user asks "research X", "summarize current state of Y", "what's the latest on Z", or compares approaches. Calls extract(action="agent") which searches the web, extracts top results, then synthesises a citation-preserving Markdown answer with one configured LLM.
fact-check
Verify a claim using adversarial search — find both supporting AND contradicting evidence.
lock-project-stack
Detect a project's manifest (pyproject.toml / package.json / go.mod / Cargo.toml), pin its library set into wet-mcp's Cabinets projectcontext, then route subsequent docs queries to the locked versions automatically.
implementation_review_supervisor
Autonomous code review — supervisor delegates to engineer subagents with knowledge base.