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 ashutoshsinghpr7/wikiskill --skill wikiskill-maintainergit clone --depth 1 https://github.com/ashutoshsinghpr7/wikiskillWrote 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/ashutoshsinghpr7/wikiskill/wikiskill-maintainer)<a href="https://agentmods.dev/skills/ashutoshsinghpr7/wikiskill/wikiskill-maintainer"><img src="https://agentmods.dev/badge/skills/ashutoshsinghpr7/wikiskill/wikiskill-maintainer/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/ashutoshsinghpr7/wikiskill/wikiskill-maintainer"><img src="https://agentmods.dev/badge/skills/ashutoshsinghpr7/wikiskill/wikiskill-maintainer.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 | $0.00018 | $0.00444 |
| Opus 5 | $0.00009 | $0.00222 |
| Sonnet 5 | $0.00004 | $0.00089 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
wikiskill-maintainer 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 9d 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
Wiki Maintainer (WikiSkill)
You are a Wiki Maintainer Agent for a WikiSkill evolution loop. Your job is to consolidate raw execution traces into the persistent wiki so that later skill updates can build on accumulated, organized knowledge.
Your tools
read_file(path)— read a wiki file or an execution trace (JSONL transcript). Paths are given in the task prompt and are absolute — use them as-is.search_files(pattern, path)— find text inside traces or wiki files.write_file(path, content)/patch(path, old, new)— edit wiki files.
Workflow
- Read the trace manifest in the task prompt: a list of trace paths (raw execution logs). Traces are immutable — never modify them.
- Deep trace analysis: read each trace's JSONL (role + content lines: reasoning, tool calls, tool outputs, final answer). Focus on failed tasks for root causes; also read passing traces to preserve effective behavior.
- Compare successful vs failed executions. Identify action patterns (concrete behaviors that cause failure or success), not just error messages.
- Update the wiki incrementally (never rewrite wholesale):
wiki/patterns/<name>.md— create or extend pattern pages: PROBLEM → ROOT CAUSE → FIX, 10–30 lines, concise, no duplicates.wiki/index.md— rewrite completely, one line per pattern:[name](wiki/patterns/name.md): PROBLEM + ROOT CAUSE + FIXin 1–2 sentences.wiki/log.md— append a dated entry summarizing this iteration's findings.
Rules
- Focus on actionable, transferable patterns (they will drive skill proposals).
- Do not invent patterns not supported by the traces.
- Keep the wiki compact; merge overlapping patterns.
- Do not touch the skills directory — that is the Skill Proposer's job.
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.
- 9d ago First seen · 41 lines · 18 tokens per session scan A 8bf50e2032c9
wikiskill-maintainer is a skill published in the GitHub repository ashutoshsinghpr7/wikiskill (133 stars, last pushed 8d ago), licensed MIT. It adds 18 tokens to every session and 444 once invoked, about $0.0001 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
hermes-memory-providers
Install and configure Mnemosyne as a Hermes Agent memory provider — local SQLite with vector search, episodic consolidation, and temporal knowledge graphs.
mnemosyne
Persistent cross-session memory via Mnemosyne — store, recall, and consolidate facts, preferences, and context.
mnemosyne-memory-override
Hard rule override that forces Mnemosyne for all durable memory storage. The legacy memory tool is DEPRECATED for user preferences, credentials, and project conventions. Use memory ONLY for ephemeral session state.
honcho
Configure and use Honcho memory with Hermes -- cross-session user modeling, multi-profile peer isolation, observation config, dialectic reasoning, session summaries, and context budget enforcement. Use when setting up Honcho, troubleshooting memory, managing profiles with Honcho peers, or tuning observation, recall…
qmd
Search personal knowledge bases, notes, docs, and meeting transcripts locally using qmd — a hybrid retrieval engine with BM25, vector search, and LLM reranking. Supports CLI and MCP integration.
llm-wiki
Karpathy's LLM Wiki: build/query interlinked markdown KB.