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 skills add kirbyju/tcia-query-skill --skill tcia-release-verificationgit 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/skills/kirbyju/tcia-query-skill/tcia-release-verification)<a href="https://agentmods.dev/skills/kirbyju/tcia-query-skill/tcia-release-verification"><img src="https://agentmods.dev/badge/skills/kirbyju/tcia-query-skill/tcia-release-verification/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/skills/kirbyju/tcia-query-skill/tcia-release-verification"><img src="https://agentmods.dev/badge/skills/kirbyju/tcia-query-skill/tcia-release-verification.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 | $0.00038 | $0.00417 |
| Opus 5.5 | $0.00015 | $0.00167 |
| Sonnet 5.5 | $0.00008 | $0.00083 |
| Haiku 4.5 | $0.00004 | $0.00042 |
Grade A, and why
tcia-release-verification 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 — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TCIA Release Verification
Use this workflow for repository maintenance. It does not authorize publishing, workflow dispatch, deployment, service restart, or data transfer.
Scope the verification
Inspect the working tree and identify the changed contract boundary. Read only the relevant sections of the repository-root references/maintainer-operations.md and the affected workflow, schema, or server documentation.
- Bundle or artifact changes require manifest, component, profile, provenance, SQLite integrity, and cross-component coherence checks.
- Correction changes require exact evidence binding, semantic-change reporting, consumption or waiver validation, and negative tests for malformed or unmatched approvals.
- MCP/REST changes require typed contract, structured-output, error-envelope, cursor, annotation, and documented-tool-surface checks.
- Workflow changes require syntax validation, immutable action pins, failure-path review, and confirmation that failed validation cannot publish a release artifact.
Execute proportionate checks
Start with the smallest deterministic tests that exercise the changed boundary. Broaden to the repository's required suite when the change affects a shared contract or release path. Use the hash-locked dependency environment for MCP/REST validation rather than the macOS system Python.
For an exact release candidate, validate the candidate artifacts themselves. Confirm declared hashes, read-only SQLite open, PRAGMA quick_check, foreign keys, required objects and keys, profile membership, source provenance, and negative incompatible or wrong-component probes. A test suite passing against fixtures does not validate a candidate artifact.
Report the result
State the commit or dirty working-tree basis, artifact fingerprint when applicable, commands run, counts or hashes that form acceptance evidence, failures or unverified checks, and the highest state actually established: local validation, publication, installation, or deployment.
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 · 31 lines · 38 tokens per session scan A 4813cd18d31e
tcia-release-verification is a skill published in the GitHub repository kirbyju/tcia-query-skill (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 38 tokens to every session and 417 once invoked, about $0.0002 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-release-verification compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tcia-release-verificationkirbyju/tcia-query-skill | Skill | 5 | 2d ago | Apache-2.0 | A | 38 | Claude Code, Codex |
| chinese-git-workflowjnMetaCode/superpowers-zh | Skill | 8.5k | 11d ago | MIT | A | 69 | Claude Code |
| atmos-profilescloudposse/atmos | Skill | 1.4k | yesterday | Apache-2.0 | A | 35 | Claude Code |
| webhook-managementhoangsonww/Claude-Code-Agent-Monitor | Skill | 1.1k | yesterday | MIT | A | 56 | Claude Code, Codex |
| monorepo-managementwshobson/agents | Skill | 42k | yesterday | MIT | C | 54 | Claude Code |
| managing-github-actions-secretsPostHog/posthog-foss | Skill | 728 | yesterday | MIT | A | 67 | Claude Code, Codex |
| postman-newman-automationLambdaTest/agent-skills | Skill | 390 | yesterday | MIT | A | 156 | Claude Code, Codex |