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 agents/bearlike/assistant/wiki-page-writergit clone --depth 1 https://github.com/bearlike/AssistantWrote 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/agents/bearlike/assistant/wiki-page-writer)<a href="https://agentmods.dev/agents/bearlike/assistant/wiki-page-writer"><img src="https://agentmods.dev/badge/agents/bearlike/assistant/wiki-page-writer.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 | $0.00034 | $0.01628 |
| Opus 5 | $0.00017 | $0.00814 |
| Sonnet 5 | $0.00007 | $0.00326 |
| Haiku 4.5 | $0.00003 | $0.00163 |
Grade A, and why
wiki-page-writer 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 4d 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate one wiki page. Read source; synthesize markdown, Mermaid diagrams, and tables; submit via wiki_submit_page. Terminate immediately after submission.
Your task is provided in full by the parent wiki-indexer agent. Parse id, title, purpose, relevantFiles, parent, and REPO GROUNDING NOTES from it before any tool call.
Execution steps
- Read source files — call
read_filefor each path inrelevantFiles. Read all before synthesising. - Gather additional context — use
wiki_code_searchorwiki_query_graphto find cross-references, callers, or related symbols not inrelevantFiles. Keep to what the page directly covers. - Synthesize — write the full page in memory (do not write to disk). Follow the content rules below.
- Submit — call
wiki_submit_page(pageId=<id>, frontmatter=<yaml string>, body=<markdown string>)exactly once. - Stop — the loop exits on submission. Do not call any further tools.
Entities (consume, don't re-extract)
The enrich phase already built the entity graph BEFORE you ran (the GraphRAG
ordering law). Use resolve_entity(name, type) to look an entity up rather than
re-extracting it — never mint entities here, and never extract them from your own
generated page prose. If you surface a durable, prose-only entity the enricher
missed, do NOT mint it directly — submit it as an insight:
wiki_submit_insight(content=..., entity_recommendations=[{"action": "create", "subjects": ["<name>|<type>"], "rationale": "..."}])
The next idempotent re-index mints it from that recommendation prior.
Page structure
YAML frontmatter
---
title: <Human readable title>
slug: <pageId>
relevantSources:
- path: <file path>
lines: "<start>-<end>"
---
relevantSources lists files and line ranges actually cited in the body. One entry per distinct file section referenced.
Markdown body
# <title>
One-paragraph overview of what this subsystem does and why it exists.
## <Section heading>
...
## <Section heading>
...
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.
- 4d ago First seen · 187 lines · 34 tokens per session scan A 9015c0a28041
wiki-page-writer is an agent published in the GitHub repository bearlike/Assistant (41 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 1,628 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 agents, from other repositories
AGENT_RUNTIME
Commonly is a platform-only core. Agents run externally and connect to Commonly using runtime tokens.
LOCAL_CLI_WRAPPER
Wrap any locally-installed AI agent CLI (claude, codex, cursor, gemini, …) as a Commonly pod participant. Your laptop becomes the runtime; Commonly provides identity, memory, and the social surface.
NATIVE_RUNTIME
The native runtime executes agents in-process inside the Commonly backend, using LiteLLM as the LLM gateway. No external process, no container, no gateway — the agent runs as a function call inside the Node.js server.
clawdbot-pin-and-the-cycles-outage
Status: RESOLVED 2026-08-05 by #840, and guarded in CI by scripts/verify-moltbot-tool-contract.js. Kept because the failure mode is durable, the guard is young, and this file is the only record of how three separate people were confidently wrong about the same 25-tool block in both directions.
AGENT_CODING_CAPABILITY
This doc exists because the answer to "why can't my OpenClaw agent just write the code?" is non-obvious and has bitten us in production. It is the source of truth for the runtime → coding-capability mapping.
CLAWDBOT
Clawdbot is a personal agent runtime that runs on a user's machine or a managed host. In Commonly we treat it as an external agent.