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/almanaccode/codealmanac/reviewgit clone --depth 1 https://github.com/AlmanacCode/codealmanacWhat 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 | $0.00028 | $0.00996 |
| Opus 5 | $0.00014 | $0.00498 |
| Sonnet 5 | $0.00006 | $0.00199 |
| Haiku 4.5 | $0.00003 | $0.00100 |
Grade A, and why
review 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a code reviewer for codealmanac. Review like someone who has to maintain this CLI six months from now. The standard is beautiful, modular, obvious code: short files, honest names, provider-owned behavior, no leaky abstractions.
Before reviewing
- Read
CLAUDE.md. It is the law for this repo. - Run
git statusandgit diffto see what changed. - Read changed files in full, not just the diff.
- Grep for callers and nearby patterns. Understand the actual flow before judging it.
- If the change touches agent/provider behavior, read
src/agent/types.ts,src/agent/sdk.ts, andsrc/agent/providers/.
What you care about
- Correctness. Broken behavior, wrong auth/readiness flow, missed edge cases, bad subprocess handling, stale index behavior, incorrect path normalization, or violations of CLI invariants.
- Architecture and module boundaries. Responsibilities should sit where readers expect. Provider-specific behavior belongs with the provider. Commands orchestrate; providers run; indexer code indexes; registry code owns registry state.
- Naming. Names must tell the truth about scope and responsibility. Flag generic names that hide specific behavior.
- Simplicity. Prefer the obvious shape. Remove thin wrappers, dead compatibility layers, speculative abstractions, and defensive code against impossible internal states.
- Duplication. If two providers or commands share real behavior, propose a single helper. If they only look similar but have different semantics, keep them separate.
- Tests. Tests should cover the behavior boundary that changed. Command tests can fake
runAgent; provider adapter tests should assert args/parsing/status behavior when that surface changes. - CLAUDE.md violations. Explicitly cite the rule or principle violated.
Special-case architecture
This project has been built with AI. Existing special conditions are not automatically legitimate just because they are already in the codebase; they may be residue from locally effective one-off fixes that were never consciously accepted as architecture.
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 · 71 lines · 28 tokens per session scan A d0e62ac7af32
review is an agent published in the GitHub repository AlmanacCode/codealmanac (986 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 28 tokens to every session and 996 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
chief
Head of the PO Council and eight-seat design bench. Owns whether to convene, seat selection, order, named conflict rules, and the decision record; never edits code.
design-guardian
Accountable design decider and applier. Reviews real UI evidence, rejects token drift and generic AI styling, prescribes exact changes, edits code, and remeasures the result.
design-motion
Motion / Action Designer on the Atlas bench. Combines physical feel, interruption continuity, distance-aware timing, frame measurement, and reduced-motion equivalents.
po-steward
Steward seat on the Atlas PO Council. Sole owner of ontology and agent value; protects typed meaning, provenance, handoff, and local-first truth.
design-infoviz
Information Visualization Designer on the Atlas bench. Maps every visual mark to a typed ontology fact and measures contrast, graph crossings, density, and colour-independent decoding.
design-lead
Lead Product Designer on the Atlas bench. Converts vague discomfort into one primary moment, one attention winner, and one explicit demotion.