Borrowing it
Nothing to install: this file belongs to kirbyju/tcia-query-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kirbyju/tcia-query-skill/main/AGENTS.mdgit clone --depth 1 https://github.com/kirbyju/tcia-query-skillWrote 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/instructions/kirbyju/tcia-query-skill/agents-md)<a href="https://agentmods.dev/instructions/kirbyju/tcia-query-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/kirbyju/tcia-query-skill/agents-md/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/instructions/kirbyju/tcia-query-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/kirbyju/tcia-query-skill/agents-md.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 | $0.00545 | $0.00545 |
| Opus 5.5 | $0.00218 | $0.00218 |
| Sonnet 5.5 | $0.00109 | $0.00109 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
tcia-query-skill AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TCIA Query Skill Repository Guidance
Project boundaries
SKILL.mdis the public agent entrypoint for TCIA discovery and access questions.references/contains focused domain and operational guidance; read only the files relevant to the task.scripts/builds, validates, installs, and queries release artifacts.mcp_server/exposes the read-only snapshot-backed MCP and REST contracts..agents/skills/contains repository-maintenance workflows, not public TCIA query instructions.evals/defines agent-routing and answer-quality cases. It is not a substitute for deterministic unit and contract tests.
Invariants
- Visible TCIA WordPress Collections and Analysis Results establish TCIA publication identity. Other systems enrich or route access but do not establish publication.
- Preserve raw source values and provenance. Keep normalized, inferred, corrected, and resolved values explicit and reviewable.
- Participant identity is dataset-scoped. Do not join participants across datasets from bare identifiers or dataset-name heuristics.
- Controlled-access metadata or manifests do not grant authorization. Never expose credentials or credential-bearing URLs.
- Distinguish local validation, published releases, installed bundles, and deployed services. Evidence for one state does not prove another.
- Preserve the separation among public DICOM, public non-DICOM, controlled-access, and Aspera/Data Retriever routes.
Working rules
- Inspect the working tree before editing and preserve unrelated user changes.
- Use the smallest relevant reference set. Do not read the entire repository before a narrow change.
- Use existing scripts for deterministic artifact operations instead of recreating their logic ad hoc.
- Unit and contract tests use local fixtures and do not publish or deploy. Run affected tests, fix failures caused by the requested change, and rerun them without requesting approval for each local step.
- Do not push, publish a release, dispatch a workflow, transfer payload data, restart a service, or deploy without explicit authorization.
- Use
$tcia-release-verificationwhen changes affect bundle schemas, release manifests, staging, correction gates, MCP/REST contracts, or release workflows.
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 · 36 lines · 545 tokens per session scan A 25af7a2157ae
tcia-query-skill AGENTS.md is an instructions file published in the GitHub repository kirbyju/tcia-query-skill (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 545 tokens to every session, about $0.0022 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 2026-09-22.
tcia-query-skill AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tcia-query-skill AGENTS.mdkirbyju/tcia-query-skill | Instructions file | 5 | 2d ago | Apache-2.0 | A | 545 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |