Skip to content
Back to search

solo-agent-guards

MarketplaceWorks with Claude CodeGitHub

Guards for running a coding agent alone: prove the test catches the bug, prove the push landed, and prove each status claim.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/robfold--solo-agent-guards/badge.svg)](/listings/robfold--solo-agent-guards)

HTML

<a href="/listings/robfold--solo-agent-guards"><img src="/api/listings/robfold--solo-agent-guards/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Claude Code:

/plugin marketplace add robfold/solo-agent-guards
/plugin install solo-agent-guards@solo-agent-guards

Other agents, with the [skills CLI](https://skills.sh):

npx skills add robfold/solo-agent-guards

Or copy the folders in [`skills/`](skills/) into your agent's skills folder (`~/.claude/skills/` for Claude Code).

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 16 lines
  1. {
  2. "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
  3. "name": "solo-agent-guards",
  4. "description": "Guards for running a coding agent alone: prove the test catches the bug, prove the push landed, and prove each status claim.",
  5. "owner": {
  6. "name": "Rob"
  7. },
  8. "plugins": [
  9. {
  10. "name": "solo-agent-guards",
  11. "description": "test-and-prove breaks the guard to show a test catches it. change-integrity checks that only your changes went up and actually landed. claim-audit checks that each status claim rests on the evidence its verb needs.",
  12. "source": "./",
  13. "category": "productivity"
  14. }
  15. ]
  16. }
README.md · README · 73 lines
  1. # solo-agent-guards
  2. English · [한국어](README.ko.md)
  3. Agent skills that stop a coding agent from saying "done" when it isn't. For people who run an AI coding agent alone, with no reviewer behind it.
  4. ![A Claude Code session: asked for tests on a refund module, the agent writes three tests, breaks each guard on its own, sees each test fail, restores the code, and reports that git diff is clean.](assets/demo.gif)
  5. <sub>Recorded in Claude Code with this plugin loaded, on a small example project. Idle time is cut and long busy stretches are sped up.</sub>
  6. - **[`test-and-prove`](skills/test-and-prove/SKILL.md): a passing test proves nothing yet.** The agent removes the guard the test protects, runs only that test, sees it fail, and restores the guard. A test that stays green guards nothing and gets rewritten. The agent reads the run count, not the exit code: `go test -run X` and `jest -t X` exit with 0 when nothing ran.
  7. - **[`change-integrity`](skills/change-integrity/SKILL.md): a successful push proves nothing yet.** The agent checks the remote SHA, the three-dot diff from the base, and what the PR or MR really contains. It stages only its own paths and leaves other sessions' unfinished work alone.
  8. - **[`claim-audit`](skills/claim-audit/SKILL.md): a success message proves nothing yet.** Before the agent reports "merged", "deployed", "passed", "running in production", or a result number, it re-reads the target and closes four gaps: a merge that is only scheduled, a check that has never failed, a number padded with its own test traffic, and a manual run reported as production. Before it takes over someone else's work, it reads the reviewer's last verdict, not the card's status.
  9. ## What it looks like
  10. With `test-and-prove`, the agent reports the break, not just the green run. This is the report from the recording above:
  11. > | Change to `billing/refunds.py` | Test run | Result |
  12. > |---|---|---|
  13. > | `if order.refunded:` → `if False:` | `test_refund_rejects_already_refunded_order` | 1 failed |
  14. > | `if amount > order.total:` → `if False:` | `test_refund_rejects_amount_over_total_and_leaves_order_untouched` | 1 failed |
  15. > | `>` → `>=` (an off-by-one that blocks a full refund) | `test_refund_marks_order_refunded` | 1 failed |
  16. >
  17. > Each run reported 1 test failing, so the test was selected and failed, not skipped. After putting the code back, `git diff billing/` is empty and the suite passes again (4 passed).
  18. With `change-integrity`, it reads what landed, not what it meant to push:
  19. > The push succeeded, but `git diff --stat origin/main...origin/fix-refund` shows 3 files and I changed 2. `config/billing.yml` is another session's unfinished work. I rebuilt the branch from `origin/main` with only my commit and pushed `fix-refund-2`. The new PR shows 2 files.
  20. With `claim-audit`, it reports what the evidence reaches, not what the tool printed:
  21. > MR !42 is not merged yet. `glab mr merge` printed "Merged!", but the API says `state: opened`, `merge_when_pipeline_succeeds: true`, `merge_commit_sha: null`: the merge is scheduled for when CI passes. The quote check says 3/3 passed, but it also passes a receipt that quotes nothing, so the check is broken; fixed by hand, the result is 2/3. Yesterday shows 7 paid orders; 4 are mock payments from curl and python-requests and 1 is an internal QA account, so 2 look like customers.
  22. <sub>The `test-and-prove` report is copied from the recording. The `change-integrity` report is an example with made-up names. The `claim-audit` report is shortened from a test run on a small example project with planted traps.</sub>
  23. ## Install
  24. Claude Code:
  25. ```
  26. /plugin marketplace add robfold/solo-agent-guards
  27. /plugin install solo-agent-guards@solo-agent-guards
  28. ```
  29. Other agents, with the [skills CLI](https://skills.sh):
  30. ```
  31. npx skills add robfold/solo-agent-guards
  32. ```
  33. Or copy the folders in [`skills/`](skills/) into your agent's skills folder (`~/.claude/skills/` for Claude Code).
  34. ## Use
  35. The skills load on their own when the request matches. `test-and-prove` loads when you ask for tests, coverage, or a flaky-test fix. `change-integrity` loads when you ask the agent to commit, push, or open a PR or MR. `claim-audit` loads right before the agent reports a status or a result number, and when you ask "is that real?". You can also call any of them by name: "write tests for the refund check and prove them".
  36. `test-and-prove` ends with numbers as the runner printed them, plus the mutation result for each new test. `change-integrity` ends with the remote SHA and the diff the PR or MR really contains. `claim-audit` ends with each claim next to the evidence it was re-read from, or a note that it could not be.
  37. ## When to use something else
  38. - **Mutation testing across a whole codebase:** [Stryker](https://stryker-mutator.io/), [mutmut](https://github.com/boxed/mutmut), or [PIT](https://pitest.org/). `test-and-prove` does the same thing by hand, for the one test you just wrote.
  39. - **Writing the test first:** [`test-driven-development`](https://github.com/obra/superpowers/tree/main/skills/test-driven-development) in obra's superpowers. TDD watches the test fail before the code exists. `test-and-prove` breaks the guard after the code exists, so it also works for tests you add to old code.
  40. - **Evidence before any claim of success:** [`verification-before-completion`](https://github.com/obra/superpowers/tree/main/skills/verification-before-completion) in obra's superpowers covers this in general. These three skills go deeper on the places where that claim most often goes wrong: tests, pushes, and status reports built on the wrong kind of evidence.
  41. - **Setting up an isolated workspace:** [`using-git-worktrees`](https://github.com/obra/superpowers/tree/main/skills/using-git-worktrees) in obra's superpowers. `change-integrity` also uses worktrees, but its job is to check what actually went up.
  42. ## Credits
  43. The rules came from corrections by the person these skills were first built for. The idea in `test-and-prove` is mutation testing. The command evidence in `change-integrity` links to the git documentation it relies on. Each gap in `claim-audit` comes from a real incident.
  44. ## License
  45. [MIT](LICENSE)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.