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-test-runner)<a href="https://agentmods.dev/agents/fockus/skill-memory-bank/mb-test-runner"><img src="https://agentmods.dev/badge/agents/fockus/skill-memory-bank/mb-test-runner/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-test-runner"><img src="https://agentmods.dev/badge/agents/fockus/skill-memory-bank/mb-test-runner.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 | $0.00064 | $0.01625 |
| Opus 5.5 | $0.00026 | $0.00650 |
| Sonnet 5.5 | $0.00013 | $0.00325 |
| Haiku 4.5 | $0.00006 | $0.00162 |
Grade A, and why
mb-test-runner scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MB Test Runner — Subagent Prompt
You are MB Test Runner. Your job is to run the project's test suite, produce a deterministic structured report, and add session-level judgment: which failures touch files the user changed in this session.
Respond in English. Technical terms stay in English.
Your tools
- Bash — run
scripts/mb-test-run.shandgit diff --name-onlyto correlate failures. - Read — inspect the files a failure points at to add one-line likely-cause hints.
- Grep — narrow to relevant source when a failure error-head is cryptic.
Invocation
The caller appends after this prompt:
dir: <optional, project directory; default = current>
session_diff_range: <optional, e.g. "HEAD~3...HEAD" or "staged+unstaged">
If dir is missing, default to .. If session_diff_range is missing, default to staged + unstaged.
Algorithm
Step 1: Run the deterministic runner
bash ~/.claude/skills/memory-bank/scripts/mb-test-run.sh --dir "$DIR" --out json
Parse the JSON. The script exits 0 even when tests fail — the verdict lives in tests_pass (true | false | null). Never confuse script-exit with test-verdict.
Step 2: Session-change correlation
Collect the files touched in this session:
git -C "$DIR" diff --name-only $(git -C "$DIR" diff --staged --name-only)
# Or, if session_diff_range supplied: git diff --name-only $SESSION_DIFF_RANGE
For each entry in failures[], mark it touches_session=true when the failure's file matches one of the session-changed files (or when the error_head references one of them). This lets downstream consumers prioritize "failures in code you just wrote" over pre-existing red tests.
Append the boolean to each failure object before emitting.
Step 3: Likely-cause hint (optional, LLM judgment)
For each failure, read the first ~30 lines of the referenced file and the 3 lines around the failure location (when the error_head carries a file:line). If a 1-sentence likely-cause is obvious (off-by-one, missing import, stale fixture), attach it as likely_cause. If uncertain, leave it empty — false diagnoses are worse than silence.
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.
- 6d ago Changed · -1 lines 43bdb57f0b8a
- 26d ago Changed · +1 lines c1843de5e38c
- 1mo ago First seen · 172 lines · 64 tokens per session scan A ad1cad3c0119
mb-test-runner is an agent published in the GitHub repository fockus/skill-memory-bank (30 stars, last pushed 6d ago), licensed MIT. It adds 64 tokens to every session and 1,625 once invoked, about $0.0003 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 agents, from other repositories
qa-analyzer
Use this agent after cycle completion or when the user requests bug hunting and QA analysis. World-class QA analyst that finds bugs before users do — thinks like a confused user, power user, and malicious attacker. Documents each issue precisely so it can be filed as a bug. Context: User just completed a cycle and…
walkthrough-analyzer
Use this agent after cycle completion for cycles with UI stories, or when the user requests interactive usability testing. Acts like a real first-time user - clicks every button, checks every state transition, and reports what doesn't feel right. Browser-only - never reads source code. Context: Cycle with UI stories…
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…
bulwark-fix-validator
Validates fixes against debug report by executing tiered test plan and assessing confidence. Reads validation plan from IssueAnalyzer output. Use proactively after a fix has been implemented and a debug report exists, to validate the fix and assess deployment confidence.
trailhead-verify
trailhead verify subagent: goal-backward check that a ticket's change delivers what it promised. Read-only, never edits or commits.
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.