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 5.5 | $0.00012 | $0.00230 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 2mo ago), licensed MIT. It adds 31 tokens to every session and 576 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 2026-08-31.
Other skills, from other repositories
github-copilot-upgrader
Use this to update the Github Copilot CLI/SDK.
winui-ui-testing
Write and run automated UI tests for Windows desktop apps (WinUI 3, WPF, WinForms, Win32) with the winapp ui harness: one batch script, assertions, input, file pickers, dialogs, screenshots, locally or in Windows Sandbox. Use when asked for UI tests or to verify a feature end to end.
create-verification-skill
Create one skill that teaches a bot how to launch, drive, and verify a specific app or project. Use only when the user explicitly asks for a verification skill.
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.
eval-agent
Run evaluation tests against an agent to assess quality and archetype resistance.
eval-workflow
Run evaluation tests against a multi-agent workflow to assess orchestration quality and failure archetype resistance.