Agent skill · Audited from source
Git Commit
skill · agulli/atlas-agentsLicence not declaredAudited 18 Oct 2026 · source dd4da722e22a
Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit dd4da722e22a and found no filesystem, network or shell access and no hard-coded secrets. What it does: Create well-structured git commits with conventional commit messages. Use when asked to commit changes, prepare a commit, or stage and push code.
Cite
Cite this page
ModelsAtlas. “Git Commit (agulli/atlas-agents)”. Retrieved 18 Oct 2026. https://modelsatlas.com/skills/agulli/git-commit
Trust audit
Audit 0.4.1 · source read 18 Oct 2026
SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 16,667 of 17,602 audited skills.
What the source does
- FilesystemNone observedNo reads or writes in the source
- NetworkNone observedNo outbound calls in the source
- ShellNone observedNo commands run in the source
- DependenciesPinnedNothing floats
- SecretsNone foundNo keys in source
Five audit layers
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | PASS | 1 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | NA | 0 |
L2 Instructions | Prompt injection, authority framing, hidden directives | PASS | 0 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: no behavioural pass, no license.
Findings (1)
LOWInventory / provenanceinv.no_license
- Why
- no LICENSE file and no repo licence
- Fix
- add a licence
Audit 0.4.1 · source sha dd4da722e22a · 18 Oct 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- Publisheragulli GitHub userOwner of the repository this skill is read from
- Source folderagulli/atlas-agents/ch09_agent_skills/skills/git-commitThe exact folder we audited
- LicenceNot declaredAs the repository states it
- Commit pinned for this verdictdd4da722e22aA new audit runs when the source changes
- Repository statusNot archivedLast push 93 days ago
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: Create well-structured git commits with conventional commit messages. Use when asked to commit changes, prepare a commit, or stage and push code.
--- name: git-commit description: Create well-structured git commits with conventional commit messages. Use when asked to commit changes, prepare a commit, or stage and push code. license: MIT compatibility: Requires git allowed-tools: Bash(git:*) --- ## Process 1. **Run `git status`** to see all changed files. Read the output carefully. 2. **Run `git diff --stat`** to understand the scope of the change. 3. **Group related changes.** If the diff contains unrelated changes (e.g., a bug fix AND a new feature), create separate commits. Do not bundle unrelated work. 4. **Stage files intentionally.** Use `git add <specific-files>`, never `git add .` unless every changed file belongs in the same logical commit. 5. **Write the commit message** using Conventional Commits format: ``` <type>(<scope>): <description> <body — explain WHY, not WHAT> <footer — references, breaking changes> ``` Types: `feat`, `fix`, `refactor`, `docs`, `test`, `chore`, `perf`, `ci` 6. **Verify before committing.** Run `git diff --cached` to review exactly what will be committed. Read the staged diff. 7. **Commit.** Run `git commit -m "..."` with the message. ## Rationalizations | Excuse | Rebuttal | |--------|----------| | "I'll just use `git add .` to save time" | Staging everything blindly leads to committing debug files, env vars, and unrelated changes. Stage intentionally. | | "The message 'fix stuff' is fine for now" | Every commit message is permanent history. Write it properly the first time. | | "I'll squash these later" | You won't. Write clean commits now. | ## Verification - [ ] `git diff --cached` output was reviewed before committing - [ ] Commit message follows Conventional Commits format - [ ] No unrelated changes were bundled into a single commit - [ ] No `.env`, `__pycache__`, or build artifacts were staged
Excerpt, first 1,848 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.
Install
Pinned to the audited commit dd4da72
git clone https://github.com/agulli/atlas-agents git -C atlas-agents checkout dd4da722e22a
The author documents no install command, so this uses the repository directly. Our verdict covers commit dd4da722e22a only.
Works in
The author has not said which agents this skill supports, and we have not tested it in any.
Audit history
Every audit, every source change
- ✓SAFE B 89 / 100
first audit · source
dd4da722e22a
Similar skills
obra/superpowers
Use when creating new skills, editing existing skills, or verifying skills work before deployment
mattpocock/skills
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
mattpocock/skills
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
Questions about Git Commit
Is Git Commit safe to install?
What can Git Commit access on my machine?
How current is this page?
Sources
- github.com/agulli/atlas-agents/tree/main/ch09_agent_skills/skill — the audited source at commit dd4da722e22a and every finding aboveObserved · 18 Oct 2026
Spotted something wrong? Report a correction · Methodology
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- Is Git Commit safe to install?
- What can Git Commit access on my machine?
- How current is this page?