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/the-teacher/active_harness/validation_proposalgit clone --depth 1 https://github.com/the-teacher/active_harnessWhat 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 | $0.00000 | $0.02229 |
| Opus 5 | $0.00000 | $0.01115 |
| Sonnet 5 | $0.00000 | $0.00446 |
| Haiku 4.5 | $0.00000 | $0.00223 |
Grade A, and why
validation_proposal 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.
How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-flight Validation & Errors (Proposal — Not Yet Implemented)
This is a design proposal, not a shipped feature. Nothing described below exists in the codebase yet. Written to think through the design and get feedback before any code is written.
The problem today
Right now, "is this agent going to work?" can only be answered by actually calling it. Validation is scattered and inconsistent:
- Unknown provider →
ArgumentError, raised deep insideattempt_model, only surfaces mid-.call. - Missing API key →
InvalidApiKeyError, raised deep inside each provider's#call, only surfaces mid-.call(and only after a request is already half-built). image true/transcribe truemodel-capability checks →ArgumentError, raised insidemodel_list, which itself only runs once.callstarts.- Unsupported audio file extension (
transcribe true,:openai) →InvalidRequestError, raised inside the provider, again only during.call.
There's no way to ask "would this agent's current config even work?" without triggering the real call path, and no single place to collect everything wrong with a config at once — you find issues one exception at a time, in whatever order the code happens to hit them.
There's also a deeper problem specific to the capability checks (image true/transcribe true, and the proposed vision true): they rely entirely on the Pricing registry knowing about the model and reporting the right category. That registry can be:
- stale (models.dev/OpenRouter data lags reality),
- wrong (categorization bugs upstream),
- empty (network/cache failure —
docs/agents/pricing.mdalready documents that a fetch/cache failure returns an empty list, not an error), - missing the model entirely (brand new or private models — today this is silently treated as "assume valid").
None of that is a reason to stop validating — but it is a reason a Pricing-based check should never be the only signal, and should be visibly distinguishable from checks that don't depend on external data at all.
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 · 158 lines · 0 tokens per session scan A 8407df37a42d
validation_proposal is an agent published in the GitHub repository the-teacher/active_harness (89 stars, last pushed 23d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,229 tokens. 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
ai-readiness-reporter
Runs the AgentRC readiness assessment on the current repository and produces a self-contained, static HTML dashboard at reports/index.html. Explains every readiness pillar, the maturity level, and an actionable remediation plan, framed by AgentRC measure → generate → maintain loop. Use when asked to assess, audit…
Custom Agent Foundry
Expert at designing and creating VS Code custom agents with optimal configurations.
Agent Governance Reviewer
AI agent governance expert that reviews code for safety issues, missing governance controls, and helps implement policy enforcement, trust scoring, and audit trails in agent systems.
chat-agents
Build AI-powered chat interfaces with AIChatAgent and useAgentChat. Messages are automatically persisted to SQLite, streams resume on disconnect, and tool calls work across server and client.
webhooks
Receive webhook events from external services and route them to dedicated agent instances. Each webhook source (repository, customer, device) can have its own agent with isolated state, persistent storage, and real-time client connections.
retries
Retry failed operations with exponential backoff and jitter. The Agents SDK provides built-in retry support for scheduled tasks, queued tasks, and a general-purpose this.retry() method for your own code.