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 Pantani/tdmcp --skill tdmcp-cookbook-examplesgit clone --depth 1 https://github.com/Pantani/tdmcpWrote 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/pantani/tdmcp/tdmcp-cookbook-examples)<a href="https://agentmods.dev/skills/pantani/tdmcp/tdmcp-cookbook-examples"><img src="https://agentmods.dev/badge/skills/pantani/tdmcp/tdmcp-cookbook-examples/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/pantani/tdmcp/tdmcp-cookbook-examples"><img src="https://agentmods.dev/badge/skills/pantani/tdmcp/tdmcp-cookbook-examples.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00094 | $0.00935 |
| Opus 5 | $0.00047 | $0.00467 |
| Sonnet 5 | $0.00019 | $0.00187 |
| Haiku 4.5 | $0.00009 | $0.00093 |
Grade A, and why
tdmcp-cookbook-examples 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 11d 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
2 near-identical copies found in the catalogue:
- tdmcp-cookbook-examples — 100% identical, 0 lines differ
- tdmcp-cookbook-examples — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tdmcp-cookbook-examples
Adds new, visually impressive examples to docs/guide/prompt-cookbook.md (EN)
and docs/pt/guide/prompt-cookbook.md (PT).
Execution mode: sub-agents (sequential curation → parallel EN+PT writing).
Phase 0: context check
Before doing anything, check:
- Does
_workspace/cookbook_candidates.mdalready exist?- YES + the user asked to "re-run" or "update" → skip curation, reuse candidates.
- YES + user gave new direction → rename old to
_workspace/cookbook_candidates_prev.md, re-curate. - NO → proceed with full Phase 1.
Phase 1: curate
Spawn the cookbook-curator agent with this prompt:
Read the task description in .Codex/agents/cookbook-curator.md and execute it.
Survey src/tools/layer1/index.ts, src/tools/layer2/index.ts, recipes/*.json,
docs/ROADMAP.md, CHANGELOG.md, and docs/guide/prompt-cookbook.md.
Produce _workspace/cookbook_candidates.md with 15-20 new cookbook candidates.
Wait for it to finish before continuing.
Phase 2: write (parallel)
Once _workspace/cookbook_candidates.md exists, spawn two writer agents in parallel:
EN writer:
Read .Codex/agents/cookbook-writer.md for your role and format rules.
Language: English.
Target file: docs/guide/prompt-cookbook.md
Candidates: _workspace/cookbook_candidates.md
Add all candidates marked for EN to the target file, following the exact format.
Write a summary to _workspace/cookbook_write_en.md when done.
PT writer:
Read .Codex/agents/cookbook-writer.md for your role and format rules.
Language: Brazilian Portuguese.
Target file: docs/pt/guide/prompt-cookbook.md
Candidates: _workspace/cookbook_candidates.md
Add all candidates to the target file, translating from the EN prompts in the
candidates file. Match the existing PT file's voice and format.
Write a summary to _workspace/cookbook_write_pt.md when done.
Phase 3: QA
After both writers finish, do a quick consistency check:
- Count entries in EN file vs PT file — the number of new entries should match.
- Spot-check 3 random new entries: verify the tool name in the result-description
exists in
src/tools/layer1/index.tsorsrc/tools/layer2/index.ts. - Check no media reference (
/examples/SLUG.mp4or.png) points to a file that already exists indocs/public/examples/under a conflicting name. - Verify both files still start with valid YAML frontmatter.
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.
- 11d ago First seen · 96 lines · 94 tokens per session scan A 2338f8b74674
tdmcp-cookbook-examples is a skill published in the GitHub repository Pantani/tdmcp (39 stars, last pushed 26d ago), licensed MIT. It adds 94 tokens to every session and 935 once invoked, about $0.0005 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 skills, from other repositories
lov-hanzi-lens
A research and infographic workflow for explaining one Chinese character, including its pronunciation, written form, history, meanings, and use in classical texts.
explainer
A tool for making narrated explainer or tutorial videos with computer-generated visuals. It can help create the script, the video, or both.
learning-mode
Hands-on mentoring: the agent scaffolds work, then pauses so the engineer writes small, meaningful code (roughly 5–15 lines) for practice. Use when the user enables learning mode, asks for guided mentoring, hands-on practice, collaborative coding, or teaching while building a feature.
iblai-api-catalog
Manage an ibl.ai organization's learning catalog via the platform API — courses, programs, pathways, resources, skills, roles, course/program metadata, plus enrollment, eligibility checks, catalog search, and course reviews. Org-wide content and enrollment operations. Use when wiring up the catalog, enrolling users…
iblai-api-analytics
Read ibl.ai analytics via the platform API — agent (chat) analytics, content (courses/programs/pathways/skills) analytics, org-wide KPIs, per-user learning data, costs, and fine-grained LLM usage (per-model/-agent/-user cost, tokens, latency) — plus generate and download Data Reports. Scope per-agent or…
iblai-api-credential
Manage an ibl.ai organization's digital credentials via the platform API — credential CRUD, user/group assignments, assertions, course-scoped credential import/export, external provider config + mapping (Accredible), and issuance analytics. Use when issuing, assigning, importing, or reporting on digital credentials…