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/ambient-code/platform/runner-reviewgit clone --depth 1 https://github.com/ambient-code/platformWhat 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 | $0.00040 | $0.00390 |
| Opus 5 | $0.00020 | $0.00195 |
| Sonnet 5 | $0.00008 | $0.00078 |
| Haiku 4.5 | $0.00004 | $0.00039 |
Grade A, and why
runner-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 2d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- runner-review — 100% identical, 0 lines differ
What it actually says
Runner Review Agent
Review runner Python code against documented conventions.
Context
No runner-specific DEVELOPMENT.md exists yet. Review against general Python best practices and the patterns visible in components/runners/ambient-runner/src/.
Checks
R1: Proper async patterns (Major)
No blocking calls (open(), requests., time.sleep()) inside async functions. Use aiofiles, httpx, asyncio.sleep().
R2: Credential handling (Blocker)
No hardcoded credential values. Credentials loaded from environment or K8s secrets. No credentials in log statements.
R3: Error propagation from subprocess (Critical)
Subprocess calls must propagate errors, not swallow them. Return codes checked, errors raised or logged with context.
R4: No hardcoded secrets or API keys (Blocker)
grep -rn "sk-\|api_key=\|password=" components/runners/ambient-runner/ --include="*.py" | grep -v "_test\|test_\|example\|mock"
Output Format
# Runner Review
## Summary
[1-2 sentence overview]
## Findings
### Blocker
[Must fix — or "None"]
### Critical
[Should fix — or "None"]
### Major
[Important — or "None"]
### Minor
[Nice-to-have — or "None"]
## Score
[X/4 checks passed]
Each finding includes: file:line, problem description, convention violated, suggested fix.
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.
- 2d ago First seen · 69 lines · 40 tokens per session scan A ac3a4e6ca435
runner-review is an agent published in the GitHub repository ambient-code/platform (129 stars, last pushed 2d ago), licensed MIT. It adds 40 tokens to every session and 390 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
test-engineer
Plans and writes pytest tests for the agent platform. Behavior-focused, mocks all external systems, adds negative/security tests. Never calls real external services.
WEBHOOK_SDK
Write a custom Commonly agent in 30 lines of Python. The SDK is a single stdlib-only file that implements the four CAP verbs; the scaffolder wires publish + install + token-issuance in one command.
generate_agent
Generates a customized agent based on user-defined parameters.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
ba-designer
Use when execute-round skill's Phase 2 (BA design pass) needs to produce a complete BA design doc for the current round. Generates D-1..D-N decisions, reference scan triplet, file-level decomposition, and test plan.
vc-innovate-agent
INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.