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 holon-run/holon --skill interlinked-markdown-wikigit clone --depth 1 https://github.com/holon-run/holonWrote 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/holon-run/holon/interlinked-markdown-wiki)<a href="https://agentmods.dev/skills/holon-run/holon/interlinked-markdown-wiki"><img src="https://agentmods.dev/badge/skills/holon-run/holon/interlinked-markdown-wiki/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/holon-run/holon/interlinked-markdown-wiki"><img src="https://agentmods.dev/badge/skills/holon-run/holon/interlinked-markdown-wiki.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 | $0.00039 | $0.01952 |
| Opus 5.5 | $0.00016 | $0.00781 |
| Sonnet 5.5 | $0.00008 | $0.00390 |
| Haiku 4.5 | $0.00004 | $0.00195 |
Grade A, and why
interlinked-markdown-wiki 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 6d 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interlinked Markdown Wiki
Use this skill when an agent must maintain a navigable knowledge base rather than merely write an isolated document. The knowledge base is a set of reviewable Markdown files whose links, sources, time semantics, and unresolved questions remain inspectable by a person and by simple repository tools.
Operating contract
- Treat the knowledge base as a bounded workspace. Read only paths and sources the operator has made available; do not discover or copy unrelated data.
- Preserve source facts. Never overwrite an immutable source snapshot, silently delete a page, or turn an inference into an organization fact.
- Default to read-only analysis or a draft. When a write is authorized, make the smallest additive or revisioned change and record what changed.
- Keep facts, interpretations, proposed changes, and unknowns in separate sections. Cite the source page or snapshot for every material claim.
- Prefer deterministic Markdown and plain-text indexes over a database or opaque embedding store. A graph or vector index may be an optional derived view, never the only copy of knowledge.
- Treat conflicting sources as unresolved until a human or an explicitly authoritative source settles the conflict.
Knowledge package layout
Use an existing workspace layout when one is already established. Otherwise create or propose this layout before writing:
knowledge/
├── pages/ # curated topic pages, one stable page per concept
├── sources/ # immutable or append-only source snapshots
├── maintenance/ # page ownership, review cadence, and open questions
├── indexes/ # generated navigation, backlinks, and unresolved links
├── reports/ # dated health and change reports
└── activity/ # append-only maintenance events
Do not create all directories merely as placeholders. Create only the parts needed for the requested operation and explain any proposed additions.
Page and source shapes
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.
- 6d ago Changed · +59 lines e730a58400cc
- 7d ago First seen · 150 lines · 39 tokens per session scan A b83a56591062
interlinked-markdown-wiki is a skill published in the GitHub repository holon-run/holon (166 stars, last pushed yesterday), licensed Apache-2.0. It adds 39 tokens to every session and 1,952 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 2026-10-09.
Other skills, from other repositories
knowledge-base
Build and maintain a company knowledge base as a wiki of interlinked markdown notes in the workspace — a private, compounding Wikipedia. Use when the user wants to start or organize a knowledge base / wiki, ingest sources (URLs, documents, pasted notes) into it, ask questions answered from it, or audit (lint) it.…
notes
Skill "notes" from Pinvou/pinvou-agent, covering ima notes, operations, write rules, examples and response handling.
openmemory
Manage persistent memory via OpenMemory MCP. TRIGGER when: user says "remember this", "save to memory", "store this", "recall", "what do you remember about", "check memory", "forget this", "delete memory", "clean up memory", or when agent forms a stable conclusion worth persisting. DO NOT TRIGGER when: user refers to…
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.
compact
Check context usage and compact the conversation from the Python REPL. Use when context is filling up, so the session is summarized and context is freed for the next stretch of work.
company-brain
How an agent should operate as one mind inside a shared Company Brain built on Caura — recall before acting, obey fleet keystones, reuse and publish skills, and report outcomes so every task compounds across the whole organization. Use this whenever you work as part of a Caura-connected team or fleet and your work…