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 agentmods add skills/agenttoolkit/altk-evolve/agent-wiki-tasksnpx skills add AgentToolkit/altk-evolve --skill agent-wiki-tasksgit clone --depth 1 https://github.com/AgentToolkit/altk-evolveWhat 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 | $0.00042 | $0.02403 |
| Opus 5 | $0.00021 | $0.01202 |
| Sonnet 5 | $0.00008 | $0.00481 |
| Haiku 4.5 | $0.00004 | $0.00240 |
Grade A, and why
agent-wiki-tasks 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 3d 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Wiki — Task Comparisons
Overview
Two cognitive moves in one pass:
- Discover — read across all summaries and identify task families (groups of sessions that attempted the same thing across trials and conditions).
- Compare — for each family, write a
tasks/<slug>__task.mdpage with a per-trial table and a findings narrative that calls out the experimental signal.
This is the cross-trajectory analysis pass of the agent-wiki family.
When to run
- After enough summaries exist that a comparative pattern is visible (typically ≥3 sessions per family).
- When the experiment design (e.g. trial × condition matrices) explicitly cries out for a comparison page.
Workflow
Step 1: Read the corpus
uv run python explorations/agent-wiki/skills/scripts/build_agent_wiki.py dump-summaries > /tmp/summaries.json
Output is a JSON array of one row per summary: {session_id, goal, family, trial, condition, tool_calls, errors, recall_used, summary_filename}.
family, trial, condition come from existing classification rules —
they may be null if no rule has matched yet.
Read the file:
Read /tmp/summaries.json
Step 2: Decide task families
For each candidate task family:
- Slug: kebab-case identifier (e.g.
extract-focal-length). - Family: short label used to group sessions (often equals slug, but
can be looser e.g.
focal-lengthfor a slugextract-focal-length). - Family-match rules: how a future session gets classified. Currently
supported:
goal_substring: [list of substrings]. A session matches the family if itsgoalcontains any substring (case-insensitive). - Tags: a few short tags.
- Intro: 1–2 sentences setting up the question.
- Findings: 2–5 bullets summarizing what the data shows. This is the actual product — a comparison page without findings is just a table.
Rules:
- A family needs ≥3 sessions. Smaller groups should not get their own page.
- Findings must be evidence-grounded. Cite tool-call counts, error counts, recall-used Y/N from the dump.
- Don't repeat what's in the table. Findings should explain why the metrics differ, not restate them.
- Use overrides for sessions whose
goaldoesn't auto-match. The override key in_config.yaml/session_family_overridesis the session id.
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.
- 3d ago First seen · 227 lines · 42 tokens per session scan A ddaf8d404a70
agent-wiki-tasks is a skill published in the GitHub repository AgentToolkit/altk-evolve (105 stars, last pushed 8d ago), licensed Apache-2.0. It adds 42 tokens to every session and 2,403 once invoked, about $0.0002 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
agent-recall
Persistent compounding memory for AI agents. 5 default MCP tools: sessionstart, sessionend, remember, recall, check. Full surface (18 tools) available with --full flag. Two-verb model: inhale (sessionstart) and exhale (sessionend). Correction-first memory with decision trail tracking, watchfor warnings, palace rooms…
shelve
Offload a closed conversation topic (or a whole imported dialog) to the memory shelf as a Markdown episode with a validated digest. Use when a topic is finished, when context grows heavy, before compaction, or when the user asks to shelve/archive part of the conversation. M0 prompt-only version — the agent does the…
speckit-tasks
Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.
speckit-clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
speckit-implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit-taskstoissues
Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.