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 to-real/cognition-workbench --skill apply-personal-cognitiongit clone --depth 1 https://github.com/to-real/cognition-workbenchWrote 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/to-real/cognition-workbench/apply-personal-cognition)<a href="https://agentmods.dev/skills/to-real/cognition-workbench/apply-personal-cognition"><img src="https://agentmods.dev/badge/skills/to-real/cognition-workbench/apply-personal-cognition/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/to-real/cognition-workbench/apply-personal-cognition"><img src="https://agentmods.dev/badge/skills/to-real/cognition-workbench/apply-personal-cognition.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 | $0.00066 | $0.00382 |
| Opus 5 | $0.00033 | $0.00191 |
| Sonnet 5 | $0.00013 | $0.00076 |
| Haiku 4.5 | $0.00007 | $0.00038 |
Grade A, and why
apply-personal-cognition 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 10d 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
调用个人认知
Treat the cognition workbench as a personal context layer, not as an authoritative fact database.
Retrieve before working
- Summarize the current task into a specific retrieval query.
- Call
retrieve_contextbefore substantive work. - If no relevant cognition is returned, continue normally without adding a knowledge notice.
- If relevant cognition is returned, use only the items that materially affect the task.
Apply with provenance
- Distinguish personal judgment from external fact.
- Respect cognition status: stable, tentative, exploring, disputed, or obsolete.
- Treat obsolete cognition as history, not default guidance.
- Surface a contradiction when current work conflicts with prior cognition.
- Verify time-sensitive external claims separately.
- Add one compact notice such as
本次调用了 3 条个人认知and make the cited items inspectable.
Do not force an old framework onto a weakly related task. Explain and discard a false association when necessary.
Offer a safe write-back
After completing the task, identify only durable new judgments, reusable frameworks, meaningful contradictions, or evidence that changes an existing view.
When such content exists:
- Call
create_update_candidateto place it in the review inbox. - Tell the user what was proposed and why it may be reusable.
- Keep temporary project details inside the project; promote them to global cognition only when they generalize.
- Call
confirm_update_candidateonly after explicit user confirmation. Never silently change formal cognition.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 38 lines · 66 tokens per session scan A 3ee833c9d444
apply-personal-cognition is a skill published in the GitHub repository to-real/cognition-workbench (0 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 382 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
wiki-retrieve
Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta…
obsidian-bases
Explain, draft, and validate Obsidian Bases .base files with filters, formulas, properties, summaries, and table, card, or list views. Use for Obsidian Bases, database-like vault views, dynamic tables, reading lists, task trackers, filters, formulas, summaries, and .base file edits.
okf
Author, maintain, and consume Open Knowledge Format (OKF) knowledge bundles — portable markdown + YAML frontmatter that both humans and agents read. Use when capturing project knowledge (services, APIs, schemas, metrics, runbooks, decisions) into an OKF bundle, when updating one after code or docs change, or when a…
shodh-memory
Persistent memory system for AI agents. Use this skill to remember context across conversations, recall relevant information, and build long-term knowledge. Activate when you need to store decisions, learnings, errors, or context that should persist beyond the current session.
vault-health-batch
Autonomous batch mode for Vault Health findings. Works through orphans, missing backlinks, and tags in batches without asking on every fix.
memex-sync
Sync Zettelkasten cards across devices via git.