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 Awish021/opencode --skill atomic-code-changesgit clone --depth 1 https://github.com/Awish021/opencodeWrote 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/awish021/opencode/atomic-code-changes)<a href="https://agentmods.dev/skills/awish021/opencode/atomic-code-changes"><img src="https://agentmods.dev/badge/skills/awish021/opencode/atomic-code-changes/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/awish021/opencode/atomic-code-changes"><img src="https://agentmods.dev/badge/skills/awish021/opencode/atomic-code-changes.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 | $0.00037 | $0.00683 |
| Opus 5.5 | $0.00015 | $0.00273 |
| Sonnet 5.5 | $0.00007 | $0.00137 |
| Haiku 4.5 | $0.00004 | $0.00068 |
Grade A, and why
atomic-code-changes 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 1mo 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Atomic Code Changes
Purpose
Keep each implementation step small enough to review, verify, and revert without dragging unrelated concerns along with it.
Core Principle
One change should have one reason to exist.
If the work needs multiple reasons, split it into multiple changes before editing.
Scope
- Applies to implementation work: fixes, features, refactors, migrations, tests, and docs tied to a code change.
- Use the smallest practical unit that still leaves the system coherent.
- Stop at task boundaries; do not roll adjacent cleanups, formatting sweeps, or opportunistic fixes into the same change.
- If a requested change is naturally broad, decompose it into ordered atomic steps first.
Atomic Change Definition
An atomic change is:
- Single-purpose: solves one problem or advances one explicit step.
- Coherent: leaves the codebase in a working, understandable state.
- Verifiable: has a clear command, inspection, or manual check.
- Reviewable: the diff can be explained in one short sentence.
- Reversible: can be backed out without removing unrelated work.
Workflow
- Name the outcome. Write the next change as one sentence: "Make X do Y."
- Choose the verification. Decide the smallest test, build, lint, or inspection that proves it.
- Edit only for that outcome. Touch the minimum files needed; defer nearby improvements.
- Run the completion gate. Verify before starting another concern.
- Reassess scope. If the next edit has a different purpose, make it a separate step.
Completion Gates
Before moving on, confirm:
- The change matches the named outcome.
- Verification passed or the remaining gap is explicitly reported.
- No unrelated formatting, cleanup, dependency, or behavior change slipped in.
- Follow-up work is noted instead of half-implemented.
Scope Tripwires
Split the work when you notice:
- "While I'm here..." edits.
- A bug fix turning into a refactor.
- A refactor requiring behavior changes.
- Tests requiring new infrastructure.
- More than one subsystem, API, or user-visible behavior changing at once.
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.
- 1mo ago First seen · 83 lines · 37 tokens per session scan A de1fcadcb736
atomic-code-changes is a skill published in the GitHub repository Awish021/opencode (11 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 683 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
release-helper
Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.