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 PCIRCLE-AI/memesh --skill memesh-reviewgit clone --depth 1 https://github.com/PCIRCLE-AI/memeshWrote 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/pcircle-ai/memesh/memesh-review)<a href="https://agentmods.dev/skills/pcircle-ai/memesh/memesh-review"><img src="https://agentmods.dev/badge/skills/pcircle-ai/memesh/memesh-review/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/skills/pcircle-ai/memesh/memesh-review"><img src="https://agentmods.dev/badge/skills/pcircle-ai/memesh/memesh-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00893 |
| Opus 5.5 | $0.00025 | $0.00357 |
| Sonnet 5.5 | $0.00012 | $0.00179 |
| Haiku 4.5 | $0.00006 | $0.00089 |
Grade A, and why
memesh-review 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 9d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MeMesh Memory Review
Review the memory database and provide actionable cleanup recommendations.
How to Access
Use CLI (works everywhere) or MCP tools (if available). See the memesh skill for auto-detect instructions.
Process
Step 1: Gather data
# Get system health
memesh status
# Get all recent memories (structured output for analysis)
memesh recall --limit 50 --json
# `--tag` filters actual tags; inspect each returned entity's `type` to group decisions, lessons, and session records.
Recall is a bounded window, not a whole-database count. For an exact health
score and factor totals, use the local GET /v1/analytics API after
memesh serve. If it is unavailable, omit the
score and label any counts from recall as sample counts.
If MCP user_patterns tool is available, also run it for work pattern analysis:
user_patterns: {}
Step 2: Analyze and report
Use the analytics result for graph-wide totals and health factors; use recalled memories to illustrate findings. Present only fields you actually obtained:
## Memory Health Report
### Overview
- Total entities: N
- Last 30 days active: N (N%)
- Knowledge types: N decisions, N patterns, N lessons, N auto-tracked
### Health Score: N/100
- Activity: N/30 points (active entities accessed in the last 30 days / all active entities)
- Quality: N/30 points (active entities with confidence > 0.7 / all active entities)
- Freshness: N/20 points (entities created in the last 7 days / all active entities, capped at 1)
- Lessons: N/20 points (`lesson_learned` entity count / 5, capped at 1)
### Quality Issues Found
**Stale (not accessed 30+ days, low confidence)**
- "entity-name" — confidence: N% — Suggest: archive?
**Verbose (5+ observations)**
- "entity-name" (N observations) — note it; there is no one-entity compression
command. If useful knowledge is spread across episodic entries, an already
running agent can prepare one MCP `work_package` for human review.
**Potential conflicts**
- "entity-A" vs "entity-B" — inspect the text and recommend an explicit
`contradicts` or `supersedes` relation; MeMesh does not judge it automatically
**Noise ratio**
- N% auto-tracked (session_keypoint, commit) vs N% intentional knowledge
- If noise > 80%: recommend more deliberate `memesh remember` usage
### Recommended Actions
1. `memesh forget --name "old-design"` (superseded)
2. Ask the current agent to prepare one MCP `work_package`; then review the staged proposal
3. `memesh remember ...` (knowledge gap in [area])
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.
- 9d ago Changed 9aed2a0eb6ce
- 22d ago Changed f7b8637293f8
- 1mo ago Changed · -21 lines 67218c177fb7
- 1mo ago Changed · +1 lines · -2 tokens per session f26a8c7a4b2f
- 1mo ago First seen · 124 lines · 64 tokens per session scan A 64231229f814
memesh-review is a skill published in the GitHub repository PCIRCLE-AI/memesh (16 stars, last pushed today), licensed MIT. It adds 62 tokens to every session and 893 once invoked, about $0.0002 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 skills, from other repositories
linglu-discipline
A set of 16 operating rules for an AI coding agent, including when to read or write long-term memory and how to report completed actions. It is designed to work with the Lingshu memory service through an MCP connection.
wenlan-handoff
End a work session. Stores durable captures, writes a narrative session log, and automatically applies typed item-level deltas to the current Space Brief. Invoked as /wenlan-handoff.
curate
Power-user audit of Wenlan's pending surfaces: accept or dismiss pending revisions (conflicts/merges), or audit pending captures (not yet confirmed). Most users want /brief for revisions; that handles the daily flow. Use /wenlan curate only for explicit deep-walk audits after bulk imports, or to walk the full queue…
wenlan
A single command entry point for Wenlan, a tool that checks its setup and connection and turns stored memories into notes. It can also open or list notes and report its current status.
wenlan-capture
Save a memory to Wenlan in flow, or save something from this conversation as one note when the user asks for a note. Use proactively when the user states a preference, makes a decision, corrects you, or shares a durable fact. Invoked as /wenlan-capture .
wenlan-recall
Search Wenlan's local memory by query. Targeted lookup, not orientation. Invoked as /wenlan-recall . Use when the user asks "do you remember", "what do you know about", "look up".