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 trsiddiqui/skill-recorder-codex --skill project-test-reportgit clone --depth 1 https://github.com/trsiddiqui/skill-recorder-codexWrote 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/trsiddiqui/skill-recorder-codex/project-test-report)<a href="https://agentmods.dev/skills/trsiddiqui/skill-recorder-codex/project-test-report"><img src="https://agentmods.dev/badge/skills/trsiddiqui/skill-recorder-codex/project-test-report/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/trsiddiqui/skill-recorder-codex/project-test-report"><img src="https://agentmods.dev/badge/skills/trsiddiqui/skill-recorder-codex/project-test-report.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 | $0.00031 | $0.00576 |
| Opus 5 | $0.00015 | $0.00288 |
| Sonnet 5 | $0.00006 | $0.00115 |
| Haiku 4.5 | $0.00003 | $0.00058 |
Grade A, and why
project-test-report 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 8d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Inspect a local repository, run its documented tests without changing project state, and summarize verified results in a concise report.
When to use
Use this skill when the requested outcome is a reproducible report containing the current Git branch, the exact test command, its exit status, and actionable failure details.
Required inputs
- The repository directory.
- The report destination.
- An optional explicit test command. When omitted, derive it from checked-in project documentation and package metadata.
Prerequisites
- Git is installed and the directory is a Git worktree.
- The repository's documented runtime and package manager are installed.
- The report destination is inside a user-approved writable directory.
Workflow
- Resolve and validate the repository directory. Read its contributor instructions and package metadata before running anything.
- Use
git branch --show-currentandgit status --shortto capture the branch and working-tree state without modifying either. - Identify the documented test command. Do not install packages, upgrade dependencies, or substitute a different command unless the user authorizes it.
- Run the test command from the repository root. Capture its exit code and a bounded summary of relevant failures; do not copy secrets or complete environment output.
- Write the report to the approved destination with the branch, working-tree state, command, exit code, pass or fail result, and concise failure summary.
Verification
- Confirm the reported branch matches
git branch --show-current. - Confirm the reported command exactly matches the command that ran.
- Confirm the report's pass or fail result matches the process exit code.
- Reopen the report and verify that it contains no credentials, tokens, or unrelated file contents.
Failure handling
- If the directory is not a Git worktree, stop and report that no branch can be verified.
- If no authoritative test command can be found, ask the user rather than guessing.
- If dependencies or runtimes are missing, report the missing prerequisite and do not install it without authorization.
- If tests time out, report the timeout separately from a test assertion failure.
- If the destination is not writable, preserve the summary in the response and ask for another destination.
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.
- 8d ago First seen · 59 lines · 31 tokens per session scan A 1a9e31a28e58
project-test-report is a skill published in the GitHub repository trsiddiqui/skill-recorder-codex (1 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 576 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other skills, from other repositories
github-copilot-upgrader
Use this to update the Github Copilot CLI/SDK.
verification-loop
This skill should be used when the user asks to "verify code", "run verification", "check quality", "validate changes", or before creating a PR. Provides comprehensive verification including build, type check, lint, tests, security scan, and diff review.
agent-session-format-check
Verify agent session format compatibility for Agent Sessions. Use when any agent CLI updates, when monitoring flags drift, or when bumping max verified versions (fixtures + docs + tests). Covers session schema, usage/limits tracking, storage backends, and discovery path contracts for all supported agents.
windows-qa-engineer
Use when testing Windows 11 desktop apps (WinForms/WPF/UWP) via UFO UIA/Win32 automation MCP. Triggers on "test this Windows app", "QA the app", "run smoke test", "click the button", "fill the form", "check the UI", "Windows automation", "UFO QA", "verify the dialog", or any Windows desktop UI testing task. Not for…
grace-verification
Design and maintain GRACE 4 verification entries, commands, scenarios, markers, and assertion evidence under .grace/verification.
auto-test-project
A structured process for testing and improving a complete software project. It runs repeated critical tests and broader quality checks across the project.