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.inspectgit 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.inspect)<a href="https://agentmods.dev/skills/emersonjds/redbar/redbar.inspect"><img src="https://agentmods.dev/badge/skills/emersonjds/redbar/redbar.inspect.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 | $0.00102 | $0.00733 |
| Opus 5 | $0.00051 | $0.00367 |
| Sonnet 5 | $0.00020 | $0.00147 |
| Haiku 4.5 | $0.00010 | $0.00073 |
Grade A, and why
redbar.inspect 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 3d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
Optional. A repo path, and/or --base <ref> to compare against something other than the detected base branch.
What this is
You do not analyze coverage. The engine does. Your job is to run it and report what it printed.
This matters: the gap list must be a measurement, not your reading of the code. Coverage is a runtime fact — which lines the test suite actually executed — and it is not visible in the source. If you guess, you produce a confident wrong answer, which is worse than no answer. Run the tool.
Outline
-
Run the engine from the project root:
npx redbar inspect $ARGUMENTSIf
redbaris not on PATH, fall back to the local build:npx tsx src/cli.ts inspect $ARGUMENTS -
If it fails because the coverage report is missing, the error already contains the exact command for this project's runner (jest and vitest do not share one, and neither do maven and gradle). Show that command to the human and stop — do not run it yourself, and do not guess a different one. Generating coverage can be slow and is the human's call.
-
Report what the engine printed. Lead with the criticality counts, then the top gaps by name. For each one worth mentioning: the symbol, the file, which layer of test it is missing (unit / integration / e2e), and why it ranks where it does (zero coverage? how many branches?).
-
Do not fix anything. This phase only reports. If the human wants the tests written, that is
/redbar.fix.
Reading the output
critical— no coverage at all, and 5+ branches. Every branch is a path nothing has ever executed. This is the row that matters.high— no coverage, and there is at least one decision in it.medium— untested but straight-line, or dense but partly covered.low— partly covered and simple.!next to a row means the symbol has no coverage anywhere in the file.
The kind column is the layer of test the gap is asking for, inferred from the file (a route → e2e, an I/O boundary → integration, everything else → unit).
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.
- 3d ago First seen · 56 lines · 102 tokens per session scan A 3fe2e9adb24d
redbar.inspect is a skill published in the GitHub repository emersonjds/redbar (6 stars, last pushed 3d ago), licensed MIT. It adds 102 tokens to every session and 733 once invoked, about $0.0005 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
dev-architecture-playbook
Route full software-development architecture work from product intent through design, implementation, testing, release, and operations. Use when the user asks for a complete development architecture, wants to know which Spellbook skills to combine, needs an execution path across…
repo-harness-check
Verification entrypoint for repo-harness workflow readiness. Runs workflow gates, task sync, contract checks, inspector, and migration dry-run before merge or release.
quick-finalize
Close out a change without the deep review loop: stage, simplify code and docs, run the project's checks, smoke test, update the changelog, self-improve, and ship. Use when the user asks to "quick finalize", "quickly finalize", "finalize quickly", "light finalize", "wrap this up quickly", "close this out without the…
ring:creating-worktrees
Creating an isolated git worktree for parallel branch work: selects the directory by priority order, verifies/adds .gitignore safety, auto-installs the detected toolchain's dependencies, runs a baseline test, and reports readiness. Use before a feature that needs isolation from the main workspace or before executing…
workflow-ship
Ship it. Runs preflight checks (typecheck, lint, tests), auto-fixes issues, then commits, pushes, and creates a PR. Bails early if preflight fixes were needed so you can review before shipping. Prompts for branch and PR target using quick multi-choice questions.
ship
Ship phase. Runs isolated integration test in a fresh worktree, creates a PR with full spec + audit report in the body, watches CI, and auto-fixes failures.