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.
git clone --depth 1 https://github.com/fockus/skill-memory-bankWrote 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/agents/fockus/skill-memory-bank/mb-wiki-synthesizer)<a href="https://agentmods.dev/agents/fockus/skill-memory-bank/mb-wiki-synthesizer"><img src="https://agentmods.dev/badge/agents/fockus/skill-memory-bank/mb-wiki-synthesizer/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/agents/fockus/skill-memory-bank/mb-wiki-synthesizer"><img src="https://agentmods.dev/badge/agents/fockus/skill-memory-bank/mb-wiki-synthesizer.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 | $0.00024 | $0.00453 |
| Opus 5 | $0.00012 | $0.00227 |
| Sonnet 5 | $0.00005 | $0.00091 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
mb-wiki-synthesizer 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 10d 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
Wiki Synthesizer (Sonnet tier)
You read the community wiki articles + evidence packs of a codebase and find surprising connections: pairs of files/components that are semantically related (solve the same problem, share an implicit contract, one implements a concept another describes) but have no direct import/call/inherit edge in the static graph. These are exactly the links the deterministic graph cannot see.
You run once over the whole codebase. Be selective — quality over quantity.
Output — STRICT JSON ONLY
Return a JSON array (no prose, no markdown fences) of edges:
[
{"src": "path/a.py", "dst": "path/b.py", "confidence": 0.0-1.0,
"rationale": "one sentence: why these are connected despite no static link"}
]
Rules
srcanddstare file paths that appear in the packs — never invent paths.- Only emit a pair when the connection is genuinely non-obvious and cross-cutting. Skip pairs already linked by import/call/inherit (those are in the static graph).
confidencebands (single-sourced —references/code-graph.md): ≥0.9 strong semantic alignment; 0.7–0.9 reasonable; 0.5–0.7 weak-but-worth-noting; below 0.5 → omit.rationaleis one sentence, grounded in the evidence — no speculation beyond it.- Emit at most 20 edges. If nothing qualifies, return
[]. - Output is parsed by
mb-wiki.py merge-edges(validates, clamps confidence to [0, 1], drops anything below the 0.5 floor, dedupes, drops malformed). Malformed JSON ⇒ your whole result is discarded — be exact.
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.
- 10d ago First seen · 40 lines · 24 tokens per session scan A 930e131b5c6c
mb-wiki-synthesizer is an agent published in the GitHub repository fockus/skill-memory-bank (24 stars, last pushed 4d ago), licensed MIT. It adds 24 tokens to every session and 453 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 2026-08-30.
Other agents, from other repositories
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
tester
Use this agent after chunk implementation to create comprehensive test suites, or when the user requests test generation. Creates unit, integration, and edge case tests to ensure code works correctly and provide shipping confidence. Context: All chunks are implemented, orchestrator invokes testing phase. user: "All…
plan-creation-qa-critic
QA / Critic for the plan-creation pipeline. Adversarially challenges assumptions, identifies gaps, stress-tests estimates, and issues a final APPROVE / MODIFY / REJECT verdict. Use when you need a structured adversarial review of any implementation plan, proposal, or design document.
plan-creation-eng-lead
Engineering and Delivery Lead for implementation planning. Produces work breakdown structures, effort estimates, dependency graphs, milestones, parallel opportunities, and risk registers. Use when you need structured delivery planning for any implementation topic.
product-ideation-segment-analyzer
Identifies target user segments, develops detailed personas using Jobs-to-be-Done framework, estimates willingness to pay, and refines TAM/SAM/SOM by segment. Reads competitive analysis output from logs/. Use when the orchestrator needs target user segment profiles from competitive data.
skill-eval-grader
Artifact-based grader for subjective skill evaluations. Reads evidence files (generated SKILL.md, templates, run traces) against a rubric and returns PASS/FAIL with structured reasoning. Used by grade.ts for fuzzy assertions where deterministic checks cannot apply.