Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/AgentToolkit/altk-evolvenpx agentmods add skills/agenttoolkit/altk-evolve/agent-wiki-consolidate-guidelinesWrote 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/agenttoolkit/altk-evolve/agent-wiki-consolidate-guidelines)<a href="https://agentmods.dev/skills/agenttoolkit/altk-evolve/agent-wiki-consolidate-guidelines"><img src="https://agentmods.dev/badge/skills/agenttoolkit/altk-evolve/agent-wiki-consolidate-guidelines.svg" alt="Measured on agentmods" 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 | $0.00056 | $0.00989 |
| Opus 5 | $0.00028 | $0.00495 |
| Sonnet 5 | $0.00011 | $0.00198 |
| Haiku 4.5 | $0.00006 | $0.00099 |
Grade A, and why
agent-wiki-consolidate-guidelines 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 7d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Wiki — Consolidate Guidelines
Overview
Spot duplicates and recurring themes across the corpus of atomic
guidelines. Author cluster pages that aggregate related variants and
record the membership in _config.yaml. Originals stay — clusters
reference them; nothing is moved or merged.
This is the cross-trajectory pattern-recognition pass of the
agent-wiki family. Run it after one or more extract-guidelines
sessions when the wiki has accumulated enough atomic guidelines that a
theme is visible.
When to run
- After a batch of
extract-guidelinesruns, when you suspect duplicates. - When
guidelines/index.md's "By tag" section has 3+ entries under the same tag and you want a canonical aggregator page for that theme. - When users complain that recall returns N near-identical hits.
Workflow
Step 1: Read the corpus
uv run python explorations/agent-wiki/skills/scripts/build_agent_wiki.py dump-guidelines > /tmp/guidelines.json
Output is a JSON array of {id, filename, title, trigger, cluster, is_cluster_page, content} for every page in guidelines/. The
is_cluster_page flag tells you which entries are existing aggregators
(__cluster.md suffix) — you will be adding new clusters, not
re-deriving existing ones.
Read the file:
Read /tmp/guidelines.json
Step 2: Decide groupings
For each candidate cluster:
- Theme: a one-line statement of the shared idea ("when system EXIF tools are missing, parse JPEG bytes directly with stdlib").
- Members: 2–6 atomic guideline ids that share that theme. Atomic only
— never include
is_cluster_page: trueentries. - Tags: 2–4 short tags that describe the theme.
Rules:
- Don't cluster unrelated guidelines just to clean up the listing. A cluster needs a real shared rule, not a shared topic.
- Don't merge content across atomic pages. Each atomic page stays whole. The cluster's body summarizes the theme and links to members.
- Don't propose a cluster for a single guideline. Wait for ≥2 members.
- Don't re-author an existing cluster unless members materially changed. Skip clusters that already exist with the same membership (
existing_clustersfield below).
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.
- 7d ago First seen · 107 lines · 56 tokens per session scan A 3e1ed91c9698
agent-wiki-consolidate-guidelines is a skill published in the GitHub repository AgentToolkit/altk-evolve (105 stars, last pushed 4d ago), licensed Apache-2.0. It adds 56 tokens to every session and 989 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 2026-08-30.
Other skills, from other repositories
memory-to-skill
Turn workflows from your MemSearch memory into reusable skills. Use when the user asks to make/create/extract/distill a skill from what they just did or from past work, review skill candidates, install a distilled skill, or 'turn this into a skill'. Manages MemSearch procedural-memory candidates under…
media-gen
Photoreal image + video generation and upscaling via fal.ai (pay-per-use, one API key, always-current models: Kling, Seedance, FLUX, nano-banana Pro, Topaz). Use for image-to-video ("animate this image", "turn this photo into a video"), photoreal video clips for websites/demos, hero video loops, upscaling…
research-notebook
Deep research on any topic via the NotebookLM CLI. Use whenever the user requests research on a topic, in any project, in any language. Triggers on phrases like "research this", "deep dive on", "do research on", "dig into", "find out about", "investigate", "look into", "research X for me". Creates or reuses a…
learn
Use when the user shares a conclusion, note, or takeaway from something they're studying — a book, course, or article — and wants it captured into their personal learning archive. Trigger phrases include "what I learned today", "notes from the book", "conclusions from chapter X", plus the explicit /learn command. Also…
wiki-article
Write a wiki article capturing structure you learned about an active project in the user's hub. Use when you grepped or spawned Explore agents to understand a project and must record that knowledge before /done, or when the user asks to "write a wiki article", "document this in the wiki", or "add this to the wiki".
session-complete
Run at end of session OR before compaction. Extracts reasoning artifacts with priority matrix, updates NEXT.md, appends to session log. Two modes: end-of-session (default) and pre-compaction (--compact). Triggers: "done", "wrap up", "session complete", "end of session", "about to compact", "context getting long".