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 mrosnerr/open-zk-kb --skill session-reviewgit clone --depth 1 https://github.com/mrosnerr/open-zk-kbWrote 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/mrosnerr/open-zk-kb/session-review)<a href="https://agentmods.dev/skills/mrosnerr/open-zk-kb/session-review"><img src="https://agentmods.dev/badge/skills/mrosnerr/open-zk-kb/session-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/mrosnerr/open-zk-kb/session-review"><img src="https://agentmods.dev/badge/skills/mrosnerr/open-zk-kb/session-review.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 | $0.00042 | $0.00400 |
| Opus 5.5 | $0.00017 | $0.00160 |
| Sonnet 5.5 | $0.00008 | $0.00080 |
| Haiku 4.5 | $0.00004 | $0.00040 |
Grade A, and why
kb-session-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 1mo 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.
What it actually says
Review this session's knowledge base usage. Score each area and act on gaps.
1. Search discipline
Scan the conversation for moments where prior context would have helped — debugging, architecture decisions, preference questions, repeated explanations. For each:
- Was knowledge-search called before acting?
- If called, was the query specific enough to surface relevant notes?
- Were results used or ignored?
2. Capture precision
First inspect session-created notes for overcapture: progress, transient outcomes, redundant concepts, immediately resolved findings, or facts better housed in code, Git, issues, OpenSpec, documentation, or logs. Report defects, but keep archive/delete changes subject to approval. Then identify only missed candidates that pass novelty, durability, behavioral-value, and canonical-home gates. Do not store plausible candidates automatically. Zero qualifying candidates is a successful review.
3. Storage quality
For each knowledge-store call made this session:
- Correct kind? (decision vs observation vs preference, etc.)
- Title scannable (3–6 words, not a sentence)?
- Summary captures the one-line takeaway?
- Guidance is an imperative instruction a future agent can act on?
- One concept per note, or bundled?
4. Output
Summarize as a scorecard:
| Area | Score | Notes |
|---|---|---|
| Search discipline | 🟢/🟡/🔴 | |
| Capture precision | 🟢/🟡/🔴 | |
| Storage quality | 🟢/🟡/🔴 |
Then list specific actions taken, qualified notes stored this session, searches that should have happened, and any remaining gaps. Capture count is not a success metric.
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.
- 1mo ago First seen · 38 lines · 42 tokens per session scan A 218110ad0e69
kb-session-review is a skill published in the GitHub repository mrosnerr/open-zk-kb (7 stars, last pushed 11d ago), licensed MIT. It adds 42 tokens to every session and 400 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 2026-08-31.
Other skills, from other repositories
forgetful-remember
Remember knowledge worth keeping — a decision made, a solution found, a preference stated, a pattern confirmed. Use when work surfaces something future sessions will need, or the user asks to remember something. Routes content to the right store (memory, document, code artifact, entity, procedure, file) and enforces…
mengram-memory
Long-term memory with 3 types (facts, events, workflows). Remember user preferences, past conversations, and learned procedures across sessions. Use when recalling what the user said before, saving important info, getting user context, or tracking completed workflows.
memory-audit-belief-duel
A guided review process for conflicting beliefs or memories. It examines cases where two conclusions cannot both be true, including conflicts between a general rule and a more specific memory.
memory-audit-discoverability
A review guide for checking whether stored memories can be found at the right time. It focuses on where memories are attached, when they are triggered, whether aliases are missing, and whether a parent has too many children.
memory-audit-pattern-extraction
A method for investigating repeated mistakes by comparing related memories and checking whether an earlier reminder failed. It looks at where the reminder was stored, when it was created, and whether it was strong enough to prevent the mistake.
memory-audit
An entry point for reviewing and maintaining an AI agent's stored memories. It describes how to remove repetition, preserve useful reasoning, and update memories when old conclusions no longer fit.