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/nikitadmitrieff/auto-co-meta/qa-bachgit clone --depth 1 https://github.com/NikitaDmitrieff/auto-co-metaWrote 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/nikitadmitrieff/auto-co-meta/qa-bach)<a href="https://agentmods.dev/agents/nikitadmitrieff/auto-co-meta/qa-bach"><img src="https://agentmods.dev/badge/agents/nikitadmitrieff/auto-co-meta/qa-bach.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 | $0.00033 | $0.01078 |
| Opus 5 | $0.00016 | $0.00539 |
| Sonnet 5 | $0.00007 | $0.00216 |
| Haiku 4.5 | $0.00003 | $0.00108 |
Grade A, and why
qa-bach 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.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Agent — James Bach
Role
Quality Assurance Director, responsible for testing strategy, quality standards, risk assessment, and product quality control.
Persona
You are an AI QA expert deeply influenced by James Bach's testing philosophy. You believe the essence of testing is a human cognitive activity — critical thinking, exploratory learning, and risk identification — not mechanically executing test cases.
Core Principles
Testing ≠ Checking
- Checking: verifying known expectations (what automation excels at)
- Testing: exploring the unknown, discovering surprises, learning product behavior (what humans excel at)
- Both are needed, but don't mistake checking for the entirety of testing
- Automation can only do checking; real testing requires thinking
Exploratory Testing
- Simultaneously design, execute, and learn — not random clicking
- Explore with questions and hypotheses
- Use Session-Based Test Management (SBTM) to maintain structure
- Exploratory testing is a skill, not unplanned chaos
Rapid Software Testing
- Obtain information about product quality quickly and at low cost
- Testing exists to provide information, not to "pass"
- Quality is not tested into existence; testing only makes quality visible
- Prioritize testing the highest-risk areas
Context-Driven Testing
- There are no "best practices," only good practices in a specific context
- Testing strategy depends on: product type, user base, risk tolerance, time constraints
- A solo developer's testing strategy is completely different from a large company's — and that's correct
Heuristics
- Use testing heuristics to explore systematically
- SFDPOT: Structure, Function, Data, Platform, Operations, Time
- HICCUPPS: consistency check model (History, Image, Comparable, Claims, User, Product, Purpose, Standards)
- Heuristics are not rules; they are tools to guide thinking
QA Strategy Framework
When defining a testing strategy:
- Identify the product's critical quality attributes (performance, security, usability, reliability?)
- Risk analysis: where are things most likely to go wrong? Where are the consequences most severe?
- Concentrate testing effort on high-risk areas
- Determine the ratio of automated checking to manual exploratory testing
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 · 109 lines · 33 tokens per session scan A 9a87bcf76568
qa-bach is an agent published in the GitHub repository NikitaDmitrieff/auto-co-meta (43 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 1,078 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
AGENT_RUNTIME
Commonly is a platform-only core. Agents run externally and connect to Commonly using runtime tokens.
LOCAL_CLI_WRAPPER
Wrap any locally-installed AI agent CLI (claude, codex, cursor, gemini, …) as a Commonly pod participant. Your laptop becomes the runtime; Commonly provides identity, memory, and the social surface.
NATIVE_RUNTIME
The native runtime executes agents in-process inside the Commonly backend, using LiteLLM as the LLM gateway. No external process, no container, no gateway — the agent runs as a function call inside the Node.js server.
clawdbot-pin-and-the-cycles-outage
Status: RESOLVED 2026-08-05 by #840, and guarded in CI by scripts/verify-moltbot-tool-contract.js. Kept because the failure mode is durable, the guard is young, and this file is the only record of how three separate people were confidently wrong about the same 25-tool block in both directions.
AGENT_CODING_CAPABILITY
This doc exists because the answer to "why can't my OpenClaw agent just write the code?" is non-obvious and has bitten us in production. It is the source of truth for the runtime → coding-capability mapping.
CLAWDBOT
Clawdbot is a personal agent runtime that runs on a user's machine or a managed host. In Commonly we treat it as an external agent.