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/saajunaid/caddis-pluginWrote 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/commands/saajunaid/caddis-plugin/verify)<a href="https://agentmods.dev/commands/saajunaid/caddis-plugin/verify"><img src="https://agentmods.dev/badge/commands/saajunaid/caddis-plugin/verify/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/commands/saajunaid/caddis-plugin/verify"><img src="https://agentmods.dev/badge/commands/saajunaid/caddis-plugin/verify.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 | $0.00015 | $0.00432 |
| Opus 5.5 | $0.00006 | $0.00173 |
| Sonnet 5.5 | $0.00003 | $0.00086 |
| Haiku 4.5 | $0.00002 | $0.00043 |
Grade A, and why
verify 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.
What it actually says
Verify
Run all project verification checks and produce a pass/fail report.
For the full verification methodology, see the skill at
skills/workflow/verification-loop/SKILL.md.
Instructions
Execute the following checks in order. Stop on critical failures.
1. Build Check
- Run the project's build command.
- If the build fails, report the errors and stop — nothing else matters until the build is fixed.
2. Type Check
- Run the type checker (e.g.,
tsc --noEmit,mypy,pyright). - Report all errors with file and line number.
3. Lint Check
- Run the project's linter (e.g.,
eslint,ruff,flake8). - Report warnings and errors.
4. Test Suite
- Run all tests with coverage enabled.
- Report pass/fail counts and coverage percentage.
5. Debug Artifact Audit
- Search source files (not test files) for
console.log,print(), ordebuggerstatements. - Report locations so they can be removed before commit.
6. Git Status
- Show uncommitted changes and files modified since last commit.
Output Format
Produce a concise verification report:
VERIFICATION: PASS / FAIL
Build: OK / FAIL
Types: OK / N errors
Lint: OK / N issues
Tests: X/Y passed, Z% coverage
Logs: OK / N debug statements found
Ready for PR: YES / NO
If any check fails, list the issues with suggested fixes below the summary.
Modes
You can scope the verification:
- quick — build + type-check only
- full — all checks (default)
- pre-commit — build, types, lint, debug audit
- pre-pr — all checks plus a search for hardcoded secrets or credentials
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 · 63 lines · 15 tokens per session scan A 191f14d84278
verify is a command published in the GitHub repository saajunaid/caddis-plugin (0 stars, last pushed today), licensed MIT. It adds 15 tokens to every session and 432 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 2026-09-09.
Other commands, from other repositories
test-feature
Test a React Native feature on the running simulator/emulator. Verifies UI, user flows, and internal state. Generates a persistent Maestro test file.
qa-pr
Device-test a GitHub pull request on iOS simulator, Android emulator, and/or physical device. Installs the PR head via rn-dev-agent and reports pass/fail with repro steps and screenshots.
run-workflow
Validate and establish the proven rn-dev-agent operating sequence before a real React Native journey — declared package manager and dependencies, read-only inventory, typed session recovery, one exclusive device, managed integration and Metro, only the requested proof, reverse-order cleanup.
lock-e2e
Promote a verified action into a frozen, locked e2e regression test. Runs the action once strict (no repair) via cdplocke2etest and freezes it to .rn-agent/e2e/ .yaml only if it passes. v1 supports param-free actions only.
specify
Command dispatcher for specify.
tester
Comprehensive testing with parallel execution capabilities.