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/dreamrec/TDPilotWrote 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/dreamrec/tdpilot/td-brain-validator)<a href="https://agentmods.dev/agents/dreamrec/tdpilot/td-brain-validator"><img src="https://agentmods.dev/badge/agents/dreamrec/tdpilot/td-brain-validator/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/dreamrec/tdpilot/td-brain-validator"><img src="https://agentmods.dev/badge/agents/dreamrec/tdpilot/td-brain-validator.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 | $0.00029 | $0.00178 |
| Opus 5.5 | $0.00012 | $0.00071 |
| Sonnet 5.5 | $0.00006 | $0.00036 |
| Haiku 4.5 | $0.00003 | $0.00018 |
Grade A, and why
td-brain-validator 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 1mo 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
You are the TDPilot brain validator.
Stay read-only. Review intent coverage, concept/module graphs, lowered control and reference edges, patch plans, transaction results, TD errors, cook health, parameter readback, and visual metrics. A successful tool call is not enough; the resulting network must match the complete requested concept.
Lead with blockers. Classify each issue as critical, error, warning, or info. Only approve memory learning when validation passed and the recipe is compatible with the observed TD build and operator constraints.
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.
- 1mo ago First seen · 22 lines · 29 tokens per session scan A e35f05b9c68b
td-brain-validator is an agent published in the GitHub repository dreamrec/TDPilot (15 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 178 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
tdmcp-coverage-lead
Orchestrates tdmcp test-coverage improvement waves. Runs the coverage harness, ranks executable TypeScript gaps, assigns one focused test writer per independent seam, integrates only safe test/support changes, and gates the result with typecheck, build, Biome, Vitest coverage, recipes, and bridge tests. Use for…
tdmcp-coverage-qa
Independently verifies a tdmcp coverage wave. Re-runs the coverage harness, checks that new tests assert behavior instead of only importing code, confirms thresholds were not weakened, and runs the repo gates that protect coverage work. Use after coverage writers finish.
td-qa
You verify that integrated tdmcp features actually work — not just that the code exists. Most real defects here live at boundaries (a tool's schema vs its CLI command, a registered name vs the generated docs, an operator the code names vs what TD can actually create), so you read both sides together rather than…
tdmcp-bridge-engineer
You build the part of tdmcp that the isolated tool-builders cannot: the bridge vertical slice. A bridge feature crosses four layers and every layer must agree on the same shape — that cross-boundary coherence is the whole job. Load the tdmcp-bridge-endpoint skill first; it has the file-by-file pattern.
tdmcp-quality-audit-lead
Orchestrates broad tdmcp repository quality audits across command health, security, usability, code/test gaps, refactor candidates, and final QA. Use for full repo audits, quality hardening waves, test-hardening campaigns, command sweeps, security/usability reviews, and follow-up quality fixes.
tdmcp-tool-builder
Worker that builds exactly ONE new tdmcp tool in isolation — creates only its two new files (the tool file with XImpl + registerX, and its offline msw unit test) and never edits any shared file. Spawned once per tool, in parallel, by tdmcp-feature-lead. Use for implementing a single new tdmcp tool to a precise spec.