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 Mark393295827/third-brain-v7-skills --skill cognitive-compilegit clone --depth 1 https://github.com/Mark393295827/third-brain-v7-skillsWrote 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/mark393295827/third-brain-v7-skills/cognitive-compile)<a href="https://agentmods.dev/skills/mark393295827/third-brain-v7-skills/cognitive-compile"><img src="https://agentmods.dev/badge/skills/mark393295827/third-brain-v7-skills/cognitive-compile/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/mark393295827/third-brain-v7-skills/cognitive-compile"><img src="https://agentmods.dev/badge/skills/mark393295827/third-brain-v7-skills/cognitive-compile.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 | $0.00032 | $0.00813 |
| Opus 5 | $0.00016 | $0.00407 |
| Sonnet 5 | $0.00006 | $0.00163 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
cognitive-compile 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 12d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cognitive Compile
<skill_contract> Source-grounded material, original question, learning or decision goal, audience, and destination. An eight-part evidence-aware mental model separating facts, mechanisms, conflicts, hypotheses, decisions, and action. Each material claim retains provenance and uncertainty, and one bounded next action answers the original question. <non_goals>Inventing missing claims, erasing contradictions or provenance, or treating interpretation as source fact.</non_goals>
Compile information into a decision-ready mental model. Compression must preserve provenance, uncertainty, contradiction, and the original question.
Usage Template
Provide: source material, original question, intended decision or learning goal, and preferred destination. Optional: existing wiki concepts to compare.
Workflow
Identify the source boundary, original question, audience, and required fidelity. Label direct source claims, external facts, and analyst inferences before synthesis.
<unknowns_gate>
If the source is inaccessible, truncated, or missing the material needed to answer the question, return INSUFFICIENT_EVIDENCE. Ask one probe only when its answer changes the compile structure; otherwise proceed with explicit unknowns.
</unknowns_gate>
Produce eight compact sections:
- Original question — the problem the material helps answer.
- Key facts — source-grounded claims with locators when available.
- Concepts and entities — stable terms worth linking.
- Patterns — mechanisms, feedback loops, or recurring structures.
- Conflicts — contradictions with the source, prior knowledge, or internal claims.
- Hypotheses — falsifiable interpretations, explicitly labeled.
- Decision support — options, tradeoffs, and what the evidence changes.
- Action — one bounded next test, note, or decision.
Prefer one durable concept note over several thin notes. Preserve source links or block references; do not rewrite immutable source notes.
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.
- 12d ago First seen · 92 lines · 32 tokens per session scan A ad227124395c
cognitive-compile is a skill published in the GitHub repository Mark393295827/third-brain-v7-skills (138 stars, last pushed 21d ago), licensed MIT. It adds 32 tokens to every session and 813 once invoked, about $0.0002 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
notebooklm
Drive NotebookLM over a programmatic CLI with no browser: turn a vault slice into an audio overview, study guide or mind map, and fold the artifacts back into the vault. Browser automation is the fallback if CLI auth breaks. Triggers: "/notebooklm", "make an audio digest of ", "podcast from the vault".
openehr-assistant
This skill should be used when a conversation touches openEHR outside a task owned by a dedicated skill — e.g. "what is an archetype?", "how do openEHR templates work?", "which composition category fits this data?", "find me a guide on X", "where do I start with openEHR modeling?" — or names openEHR concepts (ADL…
obsidian-refactor-lecture
Refactor lecture notes in Obsidian — extract concepts, definitions, and theorems from lecture notes into separate notes, turn the lecture into a "table of contents" with links, update links to the discipline MOC. Use this skill when the user asks to process, split, or refactor a lecture's notes or several lectures.…
content-documentation
Structures a technical tutorial — prerequisites, a "after reading this you'll be able to do X" goal, numbered steps with commands and checks, troubleshooting, cleanup. Doesn't write the full text: it produces a correct skeleton for the author to fill in with details. Use when "write a tutorial," "put together…
knowledge-point-tree
Build a flat, exhaustive "point tree" of every enumerable knowledge point in a bounded body of material (a textbook, a certification syllabus, a spec, an API surface, a legal code), so a learner facing a brand-new field can see the whole board at once instead of drowning in unknown unknowns. Use this whenever someone…
guide
Interactive 8-module learning path for the shipped skills, role-adaptive.