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/fallow-rs/fallow/cli-output-reviewergit clone --depth 1 https://github.com/fallow-rs/fallowWrote 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/fallow-rs/fallow/cli-output-reviewer)<a href="https://agentmods.dev/agents/fallow-rs/fallow/cli-output-reviewer"><img src="https://agentmods.dev/badge/agents/fallow-rs/fallow/cli-output-reviewer.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 | $0.00020 | $0.00934 |
| Opus 5 | $0.00010 | $0.00467 |
| Sonnet 5 | $0.00004 | $0.00187 |
| Haiku 4.5 | $0.00002 | $0.00093 |
Grade A, and why
cli-output-reviewer 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 today.
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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review changes to fallow's human-readable CLI output. This is the default user-facing surface and the most subjective.
What to check
- Information hierarchy: Most important info (file path, issue) must be the most visible. Secondary info (line numbers, suggestions) is subordinate
- Scanability: Users skim output for their files. Group by file, align columns, use consistent prefixes
- Progressive disclosure: Summary first, details behind
--verboseor section flags. Don't dump everything at once - Terminal compatibility: Colors via ANSI codes (respect
NO_COLOR/CLICOLOR), no Unicode box drawing that breaks on Windows Terminal, handle narrow terminals gracefully - Consistency across commands: check, dupes, health should feel like the same tool. Same prefix style, same severity indicators, same path formatting
- Empty states: When no issues are found, say something useful (not just silence)
- Error messages: Must tell the user what went wrong AND what to do about it
Surface-specific checks
For each human-format diff, walk this list in addition to the generic checks above:
- User-facing messages with dynamic counts pluralize the noun: any
eprintln!/println!/ format string that interpolates a count ("skipped {} files","{} issues found","{} clone groups") must branch oncount == 1for singular vs plural. Grep the diff for new format strings containing{} <noun>sand trace whether the count can be 1:git diff origin/main..HEAD | grep -nE '^\+.*"\{\} [a-z]+s'. The fix pattern islet noun = if count == 1 { "file" } else { "files" };then"{} {noun}"in the format string. JSON / SARIF / compact / codeclimate output bypasses this because the count is a structured integer, but human / markdown / stderr notes are read by humans and "skipped 1 files" is jarring. Compilation does not catch it; tests rarely catch it because most test fixtures produce 0 or many, and the singular case slips through until a real user runs the binary on a corpus that happens to skip exactly one item.
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.
- today Changed 06f02efacb02
- 4d ago First seen · 72 lines · 20 tokens per session scan A a31f7a3ed506
cli-output-reviewer is an agent published in the GitHub repository fallow-rs/fallow (4,443 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 934 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
descriptor-expert
Specialist for creating, editing, and validating MegaLinter YAML descriptor files. Use when working on linter descriptors, adding new linters, or modifying linter configurations.
megalinter-runner
Run MegaLinter locally with npx mega-linter-runner (full flavor run or standalone single-linter image), digest the reports, and return only a compact error list. Use to keep verbose linter output out of the main context. Runs and reports only — never fixes source files.
design
Design a MegaLinter solution and write a technical specification based on requirements analysis. Use after /analyze.
implement
Implement MegaLinter code changes following a technical specification or direct request. Use after /design, or directly for small focused changes.
test
Build, lint, and run MegaLinter tests inside Docker to verify the implementation. Use after /implement.
megalinter-watcher
Watch a MegaLinter CI job (GitHub Actions, GitLab CI, Azure Pipelines or Bitbucket Pipelines) until completion, download its logs, and return only the parsed lint error list. Use to keep large CI logs out of the main context. Observes only — never fixes, edits or pushes.