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 skills add winstonkoh87/Athena-Public --skill atomic-executiongit clone --depth 1 https://github.com/winstonkoh87/Athena-PublicWrote 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/skills/winstonkoh87/athena-public/atomic-execution)<a href="https://agentmods.dev/skills/winstonkoh87/athena-public/atomic-execution"><img src="https://agentmods.dev/badge/skills/winstonkoh87/athena-public/atomic-execution/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/skills/winstonkoh87/athena-public/atomic-execution"><img src="https://agentmods.dev/badge/skills/winstonkoh87/athena-public/atomic-execution.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00020 | $0.00515 |
| Opus 5 | $0.00010 | $0.00258 |
| Sonnet 5 | $0.00004 | $0.00103 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
atomic-execution scanned grade A with 1 finding 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
<verify>Command to run to verify correctness (e.g. tests or curl)</verify> What it actually says
Atomic Execution Engine
Prevents context degradation during long execution phases by breaking work down into atomic, verification-gated tasks using structured XML.
Integrated via /steal from the get-shit-done methodology.
Triggers
"execute roadmap", "start building phase", "implement this plan", "atomic execution"
Core Mechanics
When entering Execution phase, do not build monolithic features linearly in one context window. Instead:
1. XML Plan Extraction
Convert the current phase of the ROADMAP.md (or the design.md spec) into 1 or more atomic XML execution plans. If the user hasn't provided one, draft it and execute it.
Format each atomic task precisely as:
<task type="auto">
<name>Short descriptive name</name>
<files>path/to/affected/file.ext</files>
<action>
Explicit, step-by-step instructions.
Dependencies and logic.
</action>
<verify>Command to run to verify correctness (e.g. tests or curl)</verify>
<done>Definition of done</done>
</task>
2. Isolated Execution
Execute ONE <task> block at a time.
Maintain peak reasoning by not polluting the context window with previous tasks.
If a task requires subagents or isolated worktrees, trigger /git-worktree-swarm.
3. Verification Gate
After code is written, explicitly run the command specified in <verify>.
If it passes the <done> criteria, commit immediately using micro-commit.
If it fails, fix the code within the same context before proceeding to the next <task>.
4. State Management
Update STATE.md after every completed XML task block to persist progress across sessions without bloating the context window.
Always log:
- Decisions made
- Blockers encountered
- Current position in
ROADMAP.md
Reference Paths
spec-driven-dev(Pre-requisite for Execution via P107)micro-commit(Post-Execution step)
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.
- 10d ago First seen · 71 lines · 20 tokens per session scan A 204473a7fce3
atomic-execution is a skill published in the GitHub repository winstonkoh87/Athena-Public (587 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 515 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
weather
Get current weather and forecasts (no API key required).
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
travel-planner
Use for concise business travel plans that combine policy constraints, local route facts, and traveler priorities.
Launch Communications Generator
Draft launch communications: an announcement / press release, an internal support FAQ, and a customer-facing feature summary. Use for launch comms, press release, announcement, and messaging.
pinned-release-checklist
Minimal guidance-only Skill used by release-pinned compatibility examples.
clawhub-nextclaw
Use when the user wants to search external ClawHub skills or install a ClawHub skill into a NextClaw workspace's skills directory without treating ClawHub as the NextClaw marketplace.