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 ai-ecoverse/slicc --skill wikigit clone --depth 1 https://github.com/ai-ecoverse/sliccWrote 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/ai-ecoverse/slicc/wiki)<a href="https://agentmods.dev/skills/ai-ecoverse/slicc/wiki"><img src="https://agentmods.dev/badge/skills/ai-ecoverse/slicc/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/ai-ecoverse/slicc/wiki"><img src="https://agentmods.dev/badge/skills/ai-ecoverse/slicc/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 | $0.00123 | $0.00792 |
| Opus 5.5 | $0.00049 | $0.00317 |
| Sonnet 5.5 | $0.00025 | $0.00158 |
| Haiku 4.5 | $0.00012 | $0.00079 |
Grade A, and why
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 1mo 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wiki — the shared knowledge base
/shared/wiki is the compounding layer of SLICC's memory: per-cone memory files
(/workspace/CLAUDE.md) hold a small budgeted working set, session archives
hold everything raw, and the wiki in between holds synthesized knowledge as
interlinked pages every cone can read. The schema — layout, conventions, log
format — is /shared/wiki/WIKI.md; read it before editing anything. The
nightly memory-dreaming pass moves over-budget knowledge out of memory files
into wiki pages, so treat the wiki as where durable knowledge lives.
The wiki CLI
wiki search <term> # search pages by title and content (max 20 hits)
wiki list [category] # list pages, optionally one category
wiki read <note> # print a page (name, name.md, or category/name)
wiki stats # pages per category, raw sources, wikilink count
wiki links <note> # inbound + outbound wikilinks for a page
wiki orphans # pages with zero inbound links
wiki recent [n] # newest raw sources in _raw/ (default 10)
wiki log [n] # last N log.md entries (default 10)
The CLI is read-only and fails loudly when the wiki cannot be read — a zero scan is an error, never a clean bill of health.
Behaviors (from the llm-wiki pattern)
Ingest — new source in. Read the source (never edit it; session archives in
/sessions/ count as sources, cited in place). Extract entities → pages,
claims → cited sentences, relationships → [[wikilinks]] on both endpoints.
Update index.md, verify every new wikilink resolves (create a stub or flag it
missing), append ## [YYYY-MM-DD] ingest | <title> to log.md.
Query — question in. Read index.md first to discover pages, follow
cross-links, synthesize with wiki-backed citations, file the answer as a page,
update the index, log with keyword query.
Lint — health pass. wiki orphans plus a scan for broken wikilinks, stale
claims and contradictions. Fix with consent: repoint or stub broken links, add
inbound links to orphans, mark conflicts on both pages with
> ⚠ CONFLICT [YYYY-MM-DD]: <description>. Log with keyword lint and counts.
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.
- 1mo ago First seen · 66 lines · 123 tokens per session scan A 2d8cc49f6b9f
wiki is a skill published in the GitHub repository ai-ecoverse/slicc (34 stars, last pushed 2d ago), licensed Apache-2.0. It adds 123 tokens to every session and 792 once invoked, about $0.0005 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 2026-09-12.
Other skills, from other repositories
learnings
Use for repeated-looking troubleshooting, solved-issue recall, adding durable troubleshooting notes, and maintaining the local LEARNINGS archive. Reads LEARNINGS-SUMMARY.md first, follows referenced archive/source files before applying lessons, and verifies against current system evidence.
contextdb-autopilot
Automatic ContextDB session lifecycle — init, session events, checkpoints, and continuity artifacts. Use when you need AIOS context persistence without prompt injection. NOT for general task execution — only for ContextDB session management. TRIGGER: contextdb、session persist、checkpoint save.
memo
AIOS project memory — read/write/search your own memory using the memo capabilities. You (the model) decide what to remember, what to correct, and what was useful; the harness only executes your decision. Use when you want to recall prior work, persist a durable fact, supersede a wrong one, or mark a recalled memory…
aios-offload-recall
Use when recalling prior AIOS tool/browser outputs from offloaded refs; inspect Mermaid canvas first, then read only matching node-level evidence.
memory-search
Runs read-only SQL over the local EvoFlux session database (evoflux.db) for structured analysis that ordinary recall cannot answer, such as aggregating tool failures across sessions, filtering turns by role, agent, or time range, reconstructing a complete execution chain, or checking a remembered claim against what a…
map
Per-site navigation memory for tandem's shared browser. Profiles that describe a site's skeleton (routes), its durable locators, navigation recipes, and gotchas, so you navigate KNOWING instead of re-deriving the DOM each time. Use it when you start operating a site (check whether a profile already exists), when you…