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.
git clone --depth 1 https://github.com/zosmaai/pi-llm-wikiWrote 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/commands/zosmaai/pi-llm-wiki/wiki-record)<a href="https://agentmods.dev/commands/zosmaai/pi-llm-wiki/wiki-record"><img src="https://agentmods.dev/badge/commands/zosmaai/pi-llm-wiki/wiki-record.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 | $0.00028 | $0.00472 |
| Opus 5 | $0.00014 | $0.00236 |
| Sonnet 5 | $0.00006 | $0.00094 |
| Haiku 4.5 | $0.00003 | $0.00047 |
Grade A, and why
wiki-record 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 8d 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-record
Capture the trajectory of the task you just completed — the sequence of tool calls that solved it — into the wiki's working-memory layer.
This is the counterpart to source capture: instead of recording what you read, it records what you did, so the wiki compounds over your own work.
User Arguments
$ARGUMENTS
Read the LLM Wiki skill at .pi/skills/llm-wiki/SKILL.md first to understand the wiki conventions.
Steps
- Call
wiki_capture_trajectorywith:title: short descriptive phrase for the task (≤60 chars, noun phrase)outcome: optional —success(default),failure, orpartial- The extension auto-extracts the tool-call trajectory from the live session, so you usually do not pass
stepsmanually.
- Open the generated skeleton case page in
wiki/cases/and flesh out:- Task — what was requested
- Approach — the key steps and decisions (not every tool call, just the meaningful ones)
- Outcome — the result, and anything worth reusing or avoiding next time
- If the task taught a reusable pattern, run
wiki_distill_skillsand create askillpage viawiki_ensure_page(type="skill")that cites[[trajectories/TRJ-...]]. - Confirm the case (and any skill) will be surfaced by
wiki_recall/wiki_recall_skillin future sessions.
Rules:
- Only record tasks worth learning from — non-trivial debugging, refactors, integrations, multi-step workflows. Skip trivial one-shot answers.
- The raw trajectory packet under
raw/trajectories/is immutable. Edit thecase/skillpages, never the packet. - One trajectory per
wiki_capture_trajectorycall.
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.
- 8d ago First seen · 37 lines · 28 tokens per session scan A 63639d528cce
wiki-record is a command published in the GitHub repository zosmaai/pi-llm-wiki (560 stars, last pushed 3d ago), licensed MIT. It adds 28 tokens to every session and 472 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 2026-08-30.
Other commands, from other repositories
build
Rebuild context.md for a project from sources/. Usage: /mb:build [-p ] [project-id].
lint
Run health check on a project — orphans, contradictions, stale claims, gaps, suggested cross-links. Usage: /mb:lint [-p ] [project-id].
ask
Query the MindBase wiki — cited answer using hybrid search + graph expansion. Usage: /mb:ask [-p ] [--all-projects].
load
Explicitly load a project's context into session (overrides SessionStart hook). Usage: /mb:load [project-id].
init_newbrain
Onboarding interativo que personaliza AGENTS.md, Memória/ e a estrutura inicial do vault.
vault_gc
Manutenção semanal do vault: arquiva handovers antigos, valida Memória/INDEX.md e triage do INBOX.