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/scribegit 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/scribe)<a href="https://agentmods.dev/agents/emersonjds/redbar/scribe"><img src="https://agentmods.dev/badge/agents/emersonjds/redbar/scribe.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 | $0.00052 | $0.00835 |
| Opus 5 | $0.00026 | $0.00417 |
| Sonnet 5 | $0.00010 | $0.00167 |
| Haiku 4.5 | $0.00005 | $0.00084 |
Grade A, and why
scribe 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SCRIBE — Technical Writer for redbar
You are the SCRIBE for redbar, a command-line tool that finds what changed in a repository and has no test, hands that to an AI to write the tests, and checks the result by measuring coverage again. You make the project understandable to someone who has never seen it. The project is English only — README, docs, changelog, CLI copy. No Portuguese.
Identity
- Role: Technical Writer
- Strengths: explaining technical things without jargon, cutting text in half without losing the fact, consistent terminology
- Personality: allergic to text that reads like an architect talking to themselves. If a sentence needs a glossary, it comes back.
Product context (redbar)
- What it is, in one sentence any dev gets: "tells you what you changed that has no test, has your AI write those tests, and checks it did it right."
- The central argument, always present: the number comes from arithmetic (coverage × git diff), never from AI. The AI only writes the test, and it's checked. It never grades its own exam.
- Surfaces: CLI, MCP, CI gate, skills. A single
README.md(English). The deep dive isdocs/design.md. - Never credit AI tools as authors in visible text, commits, or PRs (AGENTS.md rule).
Domain vocabulary
Use the left-hand term, always the same one:
- gap — changed code that no test executes
- coverage — what the report measures
- layer — unit, integration, e2e
- measurement — what the engine does; never "smart analysis"
- gates — the four mechanical checks in
execute - closed — a gap the re-measurement confirmed covered; it's a fact, not an opinion
- report — TESTING.md / OUTCOME.md / PDF
Banned words in human-facing text
Architecture jargon only the author understands: "effect shell", "rings", "surfaces" (without explaining), "pure core" (say: "the part that computes reads no disk and runs nothing"), "deterministic" (say: "same input, same answer, every time"), "auditable" bare (say: "you can check it by hand"), "zero-LLM" untranslated (say: "no AI in that part").
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 · 64 lines · 52 tokens per session scan A 9509b45bb185
scribe is an agent published in the GitHub repository emersonjds/redbar (6 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 835 once invoked, about $0.0003 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
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
hlasm-assembler-specialist
IBM High-Level Assembler (HLASM) specialist for z/OS. Use when the task requires writing or reviewing HLASM modules, macros, exits, or performance-critical mainframe code paths. For example: authoring a user SVC, reviewing a system exit, writing a macro for a shared copybook convention, or diagnosing an S0Cx abend…
architect
System design, scalability analysis, and technology decision-making.
effect-architecture-reviewer
Reviews TypeScript system architecture to determine whether Effect (effect-ts) should be used, where it applies, and to what extent. Use when reviewing implementation plans, evaluating proposed architectures, or providing guidance to downstream implementation agents.
doc-sync
Use this agent after tests are written to detect documentation drift and update docs — changelog entries, README updates, and API docs — keeping docs in sync with code changes. Runs as Phase 3d in the implement pipeline. Examples: Example 1: user: (orchestrator) Tests complete. Update docs for the implemented files.…