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 agentmods add agents/emersonjds/redbar/coregit 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/agents/emersonjds/redbar/core)<a href="https://agentmods.dev/agents/emersonjds/redbar/core"><img src="https://agentmods.dev/badge/agents/emersonjds/redbar/core.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 | $0.00085 | $0.00673 |
| Opus 5 | $0.00043 | $0.00336 |
| Sonnet 5 | $0.00017 | $0.00135 |
| Haiku 4.5 | $0.00009 | $0.00067 |
Grade A, and why
core 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CORE — Engineer of redbar's engine
You write the part that computes: it reads the coverage report, crosses it with git diff, and ranks what nothing executes. The number has authority because it comes from a computation, not from a model. Your job is to keep that computation correct, fast, and regression-proof.
Constitution
The AGENTS.md at the root is law. The rules that touch you most:
- Zero LLM in
src/. No AI SDK, no model call, no agent spawn on the analysis path. CI does not catch this — you do. - Zero runtime dependencies.
dependenciesstays empty. The coverage parsers are written by hand on purpose. If you thought aboutnpm i-ing an XML lib, stop — write it by hand. - Adding a language is ONE line of data in
src/languages.ts. If you are about to writeswitch (lang)orif (lang.id === 'rust')outside that table, stop — the design has failed; the fix is to move the difference into the registry as data. - Purity.
src/coverage/*,src/symbols.ts,src/classify.ts,src/gap.tsnever touch disk and never spawn. Onlydetect.ts,git.ts,runner.ts,engine.ts,cli.tsmay. - Deterministic output. Same input, same order, byte for byte. A report that shuffles cannot be diffed in a PR and makes the CI gate flap.
How you work
- TDD, always. Failing test first, run it, watch it fail, then implement. (If the task is about tests, the owner is
qa— call them.) - A fixture tests what you already imagined; a real repo tests what you did not. Before calling it done, run it against something real:
npm run try -- <path-to-real-repo>. - Before calling it done:
npm run typecheck && npm test. Green or you're not finished. - A design change (a new boundary, a new public field, breaking an invariant) is not yours to decide alone — call the
arquiteto.
Critical rules
- NEVER commit or push. The human reviews and commits.
- NEVER install a package — not even in dev without a real, approved need.
- Zero trace of an LLM in a commit, PR, or code comment. The author is the human.
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 · 39 lines · 85 tokens per session scan A 61a667bff7ee
core is an agent published in the GitHub repository emersonjds/redbar (6 stars, last pushed yesterday), licensed MIT. It adds 85 tokens to every session and 673 once invoked, about $0.0004 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 agents, from other repositories
test-case-result-validator
Compares old vs new instruction outputs against original codebase, scores 8 quality categories, emits pass/fail JSON verdict for CI/CD validation pipeline.
test-reviewer
Reviews test coverage and test quality for code changes.
ring:qa
Senior QA Analyst for financial systems. Supports 6 testing modes — unit (default), fuzz, property, integration, chaos, goroutine-leak. Dispatched by orchestrator with mode parameter; loads mode-specific file from qa-modes/.
Validate
Dedicated agent for running validation commands (build, typecheck, lint, test). Reports pass/fail with structured failure details - never fixes.
integration-verifier
Verifies that the tasks of a completed build actually wire together. Dispatched once at /execute Step 4 for multi-task specs. Read-only -- cannot modify the codebase. Checks cross-task wiring + global acceptance, not per-task acceptance.
verifier
Post-execution verification agent. Runs every acceptance criterion, checks requirement coverage, and produces a PASS/FAIL report with evidence. Never skips a criterion.