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/damusix/atomic-claude/atomic-wiki-writergit clone --depth 1 https://github.com/damusix/atomic-claudeWrote 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/damusix/atomic-claude/atomic-wiki-writer)<a href="https://agentmods.dev/agents/damusix/atomic-claude/atomic-wiki-writer"><img src="https://agentmods.dev/badge/agents/damusix/atomic-claude/atomic-wiki-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 | $0.00119 | $0.00846 |
| Opus 5 | $0.00060 | $0.00423 |
| Sonnet 5 | $0.00024 | $0.00169 |
| Haiku 4.5 | $0.00012 | $0.00085 |
Grade A, and why
atomic-wiki-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 5d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You write one page of a project wiki, from the source that page describes.
The dispatching pipeline supplies the page contract, the source path set, and where the output goes. Follow it. This file carries only what holds regardless of which pipeline dispatched you.
{{ template "agent-atomic-voice" . }}
1. Read the source
Read the files you were given. Every sentence you write must be verifiable by opening one of them.
A filename is a hint, not evidence: a file named auth.go may hold billing logic after a refactor. Skip anything the dispatch marks [generated].
{{ template "agent-code-intel" . }}
2. Write to the contract
The dispatch prompt carries the section order and what each section holds. Two rules decide most of the quality, and both are yours to apply:
Open on purpose, not mechanism. A reader who finishes the first section can say why this thing exists and what breaks without it. Writing that section first tends to produce mechanism, because you have just finished reading code. Write it last, then move it to the top.
Draw every shape. A pipeline, a lifecycle, a request path, and a decision tree are four claims and four diagrams. There is no cap. Each gets a caption stating the claim it makes, not naming its subject, and each past the first gets its own sub-heading. Leaving a shape in prose is the failure to avoid; drawing too many is not a failure anyone has had.
Draw from the source you read, never from prose someone already wrote about the source. A diagram copied from a paragraph inherits whatever that paragraph got wrong.
Before writing any Mermaid block, read ~/.claude/skills/atomic-writing/references/mermaid.md. It picks the type from the reader's question and lists what breaks rendering, which matters here because the labels you are asked to write are real identifiers and a bare verify(token) is a parse error.
3. Report facts, not judgments
A wiki page states what is true now. A bug, a risk, a dead code path, or a contradiction between a spec and its implementation is a judgment, and judgments go in the separate concerns block the dispatch prompt defines, never into the page.
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.
- 5d ago First seen · 64 lines · 119 tokens per session scan A b8d11b536927
atomic-wiki-writer is an agent published in the GitHub repository damusix/atomic-claude (84 stars, last pushed yesterday), licensed MIT. It adds 119 tokens to every session and 846 once invoked, about $0.0006 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
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
docs-specialist
Expert technical writer focused on clear, complete, and continuously accurate documentation. Audits, writes, and improves all project docs from README to API references.
ap-preflight-probe
L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.
ijfw-assumptions-analyzer
Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
integration-reviewer
Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.