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 emersonjds/redbar --skill redbar.fixgit clone --depth 1 https://github.com/emersonjds/redbarWrote 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/emersonjds/redbar/redbar.fix)<a href="https://agentmods.dev/skills/emersonjds/redbar/redbar.fix"><img src="https://agentmods.dev/badge/skills/emersonjds/redbar/redbar.fix.svg" alt="Measured on agentmods" 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 | $0.00113 | $0.01127 |
| Opus 5 | $0.00056 | $0.00563 |
| Sonnet 5 | $0.00023 | $0.00225 |
| Haiku 4.5 | $0.00011 | $0.00113 |
Grade A, and why
redbar.fix 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 yesterday.
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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
Which gaps to fix. Defaults to the single most critical one — writing one good test beats writing five mediocre ones, and the human can always ask for more.
Before you start
You need .redbar/gaps.json. If it does not exist, run /redbar.inspect first — do not guess
what is untested. Coverage is a runtime fact and it is not visible in the source. Guessing
produces a confident wrong answer.
The rules that are not negotiable
- Write ONE test file per gap. Create nothing else.
- Do not modify the source file under test. If the code looks wrong, say so in your report — do not fix it. You were asked to write a test, and a test that changes the code it tests proves nothing.
- Run the test you wrote. Not the whole suite — just yours.
- Never leave a red test in the repository. If it fails twice, delete the file and mark the gap
needs-human. One failing test leaking into a branch erases the value of every passing one. - Follow the convention. Do not improvise a style. The whole point of redbar is that tests come out looking like the library's docs, not like whatever the model felt like that morning.
Outline
-
Read the gaps:
cat .redbar/gaps.jsonPick the target(s) from
$ARGUMENTS, or the highest-severitygap if no argument was given. Order:critical→high→medium→low, and byscorewithin a band. -
Read the convention for that gap's layer. The gap's
kindfield decides which one:kindRead unitconventions/<lang>/unit.mdintegrationconventions/<lang>/integration.mde2econventions/<lang>/e2e.mdAlso read
.redbar/conventions/<lang>/<kind>.mdif it exists — those are the project's own deltas, and they win over the shipped standard.Read it every time. Do not work from memory of what a good test looks like — that memory is the model's house style, which is the exact thing this tool exists to prevent.
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.
- yesterday First seen · 93 lines · 113 tokens per session scan A 489593dc439e
redbar.fix is a skill published in the GitHub repository emersonjds/redbar (6 stars, last pushed yesterday), licensed MIT. It adds 113 tokens to every session and 1,127 once invoked, about $0.0006 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 2026-09-04.
Other skills, from other repositories
tdd-workflow
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
memstack-development-test-writer
Use this skill when the user says 'write tests', 'add tests', 'test coverage', 'unit tests', 'integration tests', 'component tests', 'mocking', 'edge cases', or needs to generate tests with proper mocking and edge case coverage. Do NOT use for refactoring plans or database migrations.
test-commander
Generate unit, integration, E2E, and visual regression tests following the Testing Trophy methodology (80% integration). Covers Vitest/Jest, Testing Library, Playwright, MSW for API mocking, snapshot strategy, visual regression (Chromatic/Percy/Playwright), test factories with Faker, and CI sharding. Use when user…
mandu-testing
Testing patterns for Mandu applications. Use when writing unit tests, integration tests, or E2E tests. Triggers on test, spec, Bun test, Playwright, or testing tasks.
testing-strategy
Choose the right test type for every change — unit, integration, contract, end-to-end, property-based, mutation, fuzz. Use when adding tests to a new feature, deciding what to test for a bug fix, designing a test pyramid for a service, evaluating coverage targets, or untangling a slow test suite. Stack-agnostic…
test-sweep
Run all test suites (unit, integration, API, E2E) and aggregate results into a summary report. Use after completing execution slices or before the Review Gate.