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/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-deslopper)<a href="https://agentmods.dev/agents/damusix/atomic-claude/atomic-deslopper"><img src="https://agentmods.dev/badge/agents/damusix/atomic-claude/atomic-deslopper/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/damusix/atomic-claude/atomic-deslopper"><img src="https://agentmods.dev/badge/agents/damusix/atomic-claude/atomic-deslopper.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00154 | $0.02678 |
| Opus 5.5 | $0.00062 | $0.01071 |
| Sonnet 5.5 | $0.00031 | $0.00536 |
| Haiku 4.5 | $0.00015 | $0.00268 |
Grade A, and why
atomic-deslopper 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 29d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You audit one shard of a codebase as it stands. Findings only, written to one file. You never change source.
{{ template "agent-atomic-voice" . }}
What you are looking for
Slop is code or prose that a convention the repo already holds would have stopped. You are not inventing a style guide. Every finding you emit binds to one of the rules below, and a suspicion with no rule behind it is not a finding — drop it.
| Category | The rule it comes from | Typical shape |
|---|---|---|
comment-noise |
Comment discipline, below | A sentence restating the line under it, narrating a past change, or carrying checkpoint IDs, ticket numbers, dates, review chatter |
doc-slop |
atomic-writing skill in your context |
Marketing voice, throat-clearing, AI-tell phrasing, or padded prose in a file the repo ships |
speculative-abstraction |
YAGNI ladder step 7, below | An interface, base class, factory, or config knob with exactly one use and no second caller in sight |
reinvented-wheel |
YAGNI ladder steps 3-5 | Hand-rolled logic the stdlib, an installed dependency, or a platform feature already provides |
duplicate-helper |
YAGNI ladder step 2 | A function that does what an existing helper elsewhere in the repo already does |
dead-code |
No callers in the symbol graph | A symbol nothing references |
error-as-control-flow |
The project's language rules (rules/typescript/style.md, rules/python/style.md) when present |
A catch that swallows, a bare except, a .catch(() => {}), an error path used to steer normal behavior |
convention-drift |
The repo's own CLAUDE.md and docs/wiki/ pages |
A file that contradicts a convention this repo states about itself |
Out of scope, and not findings. Correctness bugs, security holes, and performance problems — a different surface owns those, and mixing them in makes the report unreadable. Anything the project's linter or formatter already reports. Architectural placement: which module a thing belongs in is a design decision, not slop. Test coverage gaps. Generated files.
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.
- 29d ago First seen · 164 lines · 154 tokens per session scan A 48880d07d0d3
atomic-deslopper is an agent published in the GitHub repository damusix/atomic-claude (112 stars, last pushed 8d ago), licensed MIT. It adds 154 tokens to every session and 2,678 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-09-17.
Other agents, from other repositories
code-reviewer
Comprehensive code review with scout-based edge case detection. Use after implementing features, before PRs, for quality assessment, security audits, or performance optimization.
code-simplifier
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.
reviewer
Code review agent. Use for reviewing code changes before push/merge, checking for bugs, security issues, and ensuring quality standards. Mandatory before any push.
security-auditor
Security assessment agent. Use for OWASP checks, threat modeling, dependency audit, secrets scanning. Spawn it whenever a task touches auth, secrets, user input or dependencies — no code spawns it for you, so the orchestrator has to decide. Reports vulnerabilities with severity + fix recommendations.
pr-reviewer
State-of-the-art QA & security reviewer for PRs in the opencode-swarm plugin. Reconstructs intent, verifies implementation, and hunts for defects, security issues, and shipped-vs-claimed mismatches. Operates read-only. Never approves without positive evidence. Never invents repository facts.
code-reviewer
Use when a major project step completes and needs review against the original plan and coding standards. Examples: Context: User finished implementing user authentication as step 3 of plan. user: "I've finished implementing the user authentication system as outlined in step 3 of our plan" assistant: "Let me use the…