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 DiUS/agent-toolkit --skill knowledge-curationgit clone --depth 1 https://github.com/DiUS/agent-toolkitWrote 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/dius/agent-toolkit/knowledge-curation)<a href="https://agentmods.dev/skills/dius/agent-toolkit/knowledge-curation"><img src="https://agentmods.dev/badge/skills/dius/agent-toolkit/knowledge-curation/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/dius/agent-toolkit/knowledge-curation"><img src="https://agentmods.dev/badge/skills/dius/agent-toolkit/knowledge-curation.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 | $0.00102 | $0.05495 |
| Opus 5 | $0.00051 | $0.02747 |
| Sonnet 5 | $0.00020 | $0.01099 |
| Haiku 4.5 | $0.00010 | $0.00549 |
Grade A, and why
knowledge-curation 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 8d 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 — 402 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Curating knowledge
Role: Senior BA with PO judgement. Precise elicitation, never guess, decompose rather than summarise. Model: latest Claude Opus.
Conventions — load these before extracting
This skill writes into a knowledge base with fixed tiers, IDs, and a front-matter schema. Load these before creating any file:
references/conventions/structure.md— the tree, the tiers, where each kind of fact belongs, and how to reference by ID.references/conventions/ba-principles.md— the non-negotiables (coverage first, label provenance, ownership is authority not inference, surface conflicts).references/conventions/knowledge-boundary.md— the central-vs-provisional placement test for business vs. technology content.references/conventions/front-matter.md— the six-line front-matter schema, thebasis/statusvocabularies, and the ID conventions.
Workspace setup — before first curation
Curated knowledge is written to knowledge/ at the workspace root (never inside
the skill). Don't judge the directory's state by eye and decide what to copy — that's
a script's job, and it's additive by construction so there is no destructive branch to
get wrong. Run it and branch on the exit code:
bash <this-skill>/scripts/setup-workspace.sh <workspace-root>
It scaffolds a fresh knowledge/ (empty registries — platform/coverage.md,
platform/data-ownership.md, platform/service-domains.md, an empty
platform/constraints/ tier, sources/manifest.md, decisions/README.md), or, if
one already exists, adds only the files that are missing. It never overwrites, so
re-running is always safe: an interrupted first run is repaired by running it again.
Branch on the exit code — do not write into knowledge/ by any other path:
0→ ready. TheSTATE=line reportscreated(new),extended(this skill's corpus, or its own partial scaffold — missing files filled in), oradopted. Proceed to curation. The setup also printsAGENTS_MD=present|absent— see below.2(blocked) →knowledgeexists as a file or symlink, not a directory. Stop. Tell the user; do not write through it.3(needs-adopt) → aknowledge/folder exists that this skill didn't create (no corpus markers, and it holds foreign files). Stop and ask whether to curate into a different path, adopt this folder, or stop. Only on an explicit yes, re-run with--adoptappended. Never pass--adopton your own judgement — adoption means writing into someone else's directory, so it takes a human's word in chat.1→ usage/setup error (bad arguments, or the scaffold is missing). Fix and re-run.
What ships with it
45 files 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.
- assets/knowledge-base/knowledge/AGENTS.md 1.5 KB
- assets/knowledge-base/knowledge/decisions/README.md 870 B
- assets/knowledge-base/knowledge/domains/README.md 474 B
- assets/knowledge-base/knowledge/index.md 1.3 KB
- assets/knowledge-base/knowledge/platform/constraints/README.md 448 B
- assets/knowledge-base/knowledge/platform/coverage.md 1.2 KB
- assets/knowledge-base/knowledge/platform/data-ownership.md 1.6 KB
- assets/knowledge-base/knowledge/platform/data-schema/README.md 430 B
- assets/knowledge-base/knowledge/platform/index.md 930 B
- assets/knowledge-base/knowledge/platform/service-domains.md 710 B
- assets/knowledge-base/knowledge/questions/index.md 1.0 KB
- assets/knowledge-base/knowledge/sources/manifest.md 1.4 KB
- README.md 5.3 KB
- references/business-vs-tech-routing.md 2.9 KB
- references/completeness.md 3.2 KB
- references/conventions/ba-principles.md 3.1 KB
- references/conventions/front-matter.md 12 KB
- references/conventions/knowledge-boundary.md 3.0 KB
- references/conventions/structure.md 8.9 KB
- references/elicitation.md 6.3 KB
- references/grouping.md 2.4 KB
- references/knowledge/configuration.md 955 B
- references/knowledge/constraint.md 1.5 KB
- references/knowledge/data-consumed.md 1.3 KB
- references/knowledge/data-owned.md 1.1 KB
- references/knowledge/data-schema.md 1.0 KB
- references/knowledge/domain-index.md 2.8 KB
- references/knowledge/feature-index.md 2.0 KB
- references/knowledge/glossary.md 1.1 KB
- references/knowledge/integration.md 2.3 KB
- references/knowledge/journey.md 1.6 KB
- references/knowledge/open-question.md 2.0 KB
- references/knowledge/rule.md 1.9 KB
- references/knowledge/ui-specification.md 1.2 KB
- references/knowledge/user-persona.md 1.0 KB
- references/knowledge/workflow.md 8.4 KB
- references/registry-templates/adr.md 876 B
- references/registry-templates/coverage.md 1.4 KB
- references/registry-templates/data-ownership.md 1.7 KB
- references/registry-templates/sources-manifest.md 1.1 KB
- scripts/check-examples.sh 849 B runs code
- scripts/check-frontmatter.sh 4.9 KB runs code
- scripts/check-placement.sh 1.7 KB runs code
- scripts/check-structure.sh 2.9 KB runs code
- scripts/setup-workspace.sh 5.3 KB runs code
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.
- 8d ago First seen · 402 lines · 102 tokens per session scan A 548c1ce9fe4f
knowledge-curation is a skill published in the GitHub repository DiUS/agent-toolkit (2 stars, last pushed 4d ago), licensed MIT. It adds 102 tokens to every session and 5,495 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 2026-09-04.
Other skills, from other repositories
incident
Incident response and postmortem generation from git/deploy context. When something breaks in production, this skill builds a timeline, identifies the probable cause, and generates a structured postmortem document. Flags: --since, --service, --sev, --revert, --comms, --dry-run.
presentation
Generate PowerPoint (PPTX) presentations from a topic, outline, or content file. Creates professional slides using python-pptx with consistent theming and typography. Modes: [topic] (from scratch), from [file] (from markdown), --slides N, --theme dark|light|corporate, --outline-only, --out [path], --lang [code].
export-human-spec
Generate a human-readable natural language specification document (Markdown) from a VDM-SL formal specification. Translates types, invariants, pre/post-conditions, and operations into clear prose that domain experts, project managers, and non-technical stakeholders can understand and review — without needing to learn…
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
sheet-music-publisher
Converts mastered audio to sheet music and creates printable songbooks. Use after mastering when the user wants sheet music or a songbook for their album.