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 agents/fockus/skill-memory-bank/mb-tooling-coregit 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-tooling-core)<a href="https://agentmods.dev/agents/fockus/skill-memory-bank/mb-tooling-core"><img src="https://agentmods.dev/badge/agents/fockus/skill-memory-bank/mb-tooling-core.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 | $0.00042 | $0.00565 |
| Opus 5 | $0.00021 | $0.00282 |
| Sonnet 5 | $0.00008 | $0.00113 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
mb-tooling-core 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.
What it actually says
MB Tooling Core — code-understanding routing
This is a prepended partial, not an agent. /mb work inlines this block ahead of the
role-specific agent delta. It carries the single routing table every MB implementer uses to
understand code before touching it.
Code-understanding tools (graph-first, fail-open)
For code-understanding questions, prefer Memory Bank graph tools over grep:
| Intent | Token | Canonical command |
|---|---|---|
| ambiguous "where is the logic for X?" / "find similar implementation" (fuzzy code-context) | code_context |
scripts/mb-code-context.py |
| "who calls / imports / defines X?" (direct structural query) | graph_neighbors |
scripts/mb-graph-query.py neighbors |
| "change impact" / "reverse deps" / blast-radius | graph_impact |
scripts/mb-graph-query.py impact |
| "which tests cover this file/symbol?" | graph_tests |
scripts/mb-graph-query.py tests |
concept search (BM25 default, --backend embeddings opt-in) |
search_code |
scripts/mb-semantic-search.py |
| decisions / "why did we …?" | recall |
/mb recall <query> |
Fail open: missing graph, stale graph, missing semantic provider, or unavailable native extension must not block work — CLI scripts / Grep / Glob / Read are the universal fallback.
These indexes are optional; if absent or stale, fall back to Grep/Glob/Read — never block.
- On a stale graph you MAY run
python3 scripts/mb-graph-query.py catchup --graph <bank>/codebase/graph.json --src-root . --jsononce (bounded single-consumer catch-up: non-blockingcodebase/.graph.lockflock, hardMB_GRAPH_CATCHUP_BUDGETbudget with process-group kill, cooldown after failure, opt-in layers preserved) — never callmb-codegraph.py --applydirectly from an agent and never take ad-hoc locks. If the result islocked/cooldown/timed_out, proceed on the stale graph and fall back toGrep/Glob/Read— never block.
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 · 29 lines · 42 tokens per session scan A d941c078e14a
mb-tooling-core is an agent published in the GitHub repository fockus/skill-memory-bank (24 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 565 once invoked, about $0.0002 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
tool-conflict-agent
An agent with conflicting tool configurations.
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.…
verifier
Verification agent for /craft:research-verify. Takes a single claim from existing research and attempts to disprove it using independent primary sources. Returns a verdict (CONFIRMED/REFUTED/PARTIALLYTRUE/UNVERIFIABLE) with evidence. NOT a researcher. Does not discover new topics or cast a wide net. Takes one claim…
invalid-infer-type
Review pull requests.
invalid-target
Review pull requests.
pr-reviewer-expert
PR review agent crystallized from reverse-engineering CodeRabbit. Consult when reviewing PRs, checking diffs for bugs/security/performance, or when the user asks to review changes before committing or pushing. Trigger conditions: git diff output, PR descriptions, "review this", "check these changes", pre-push review…