Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add jaroslavsoucek-art/Giovanni/plugin install giovanniWrote 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/jaroslavsoucek-art/giovanni/consistency-review)<a href="https://agentmods.dev/skills/jaroslavsoucek-art/giovanni/consistency-review"><img src="https://agentmods.dev/badge/skills/jaroslavsoucek-art/giovanni/consistency-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jaroslavsoucek-art/giovanni/consistency-review"><img src="https://agentmods.dev/badge/skills/jaroslavsoucek-art/giovanni/consistency-review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00044 | $0.01309 |
| Opus 5.5 | $0.00018 | $0.00524 |
| Sonnet 5.5 | $0.00009 | $0.00262 |
| Haiku 4.5 | $0.00004 | $0.00131 |
Grade A, and why
consistency-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 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/giovanni:consistency-review
Triage the findings of a /giovanni:consistency-check run, one by one, with the principal as decision-maker. This command is a thin shell — the triage procedure lives in ${CLAUDE_PLUGIN_ROOT}/skills/consistency-review/procedure.md. This file is the invocation contract.
Like /giovanni:digest, this command routes to a workflow procedure rather than an agent: triage is interactive (per-finding verdicts from the principal), so it runs in the main thread.
Usage
/giovanni:consistency-review <YYYY-MM-DD> # triage the report for that date
/giovanni:consistency-review # defaults to the most recent report
Argument syntax
| Arg | Type | Default | Meaning |
|---|---|---|---|
<YYYY-MM-DD> |
positional date | most recent report | Which report in memory/audits/consistency/ to triage. |
Pre-flight (binding — STOP on failure)
- CWD check. Working directory is a Giovanni repo (presence of
memory/CLAUDE_MEMORY.md+knowledge/<constitution>.md). Otherwise STOP. - Report file present.
memory/audits/consistency/<YYYY-MM-DD>.mdexists (after resolving the default). Missing → STOP:ERROR: no consistency report for <YYYY-MM-DD>. Run /giovanni:consistency-check first. - State file present.
memory/audits/consistency/_state.mdexists. If missing → seed per the/giovanni:consistency-checkauto-seed rules (shadow window starts today, 28 days) and surface an advisory — a review without a state file can't record precision. - Run entry present.
_state.mdcontains a## Run <YYYY-MM-DD>entry for the report being reviewed. Missing → STOP with diagnostic (report and state are written together by the agent; a missing entry means a corrupted run). - Not already reviewed. If the run entry has
review_status: complete, warn and confirm at prompt (y/N) before re-reviewing — a re-review overwrites the prior verdict counts.
Execution flow
- Run pre-flight. STOP on any failure.
- Run the workflow procedure per
${CLAUDE_PLUGIN_ROOT}/skills/consistency-review/procedure.md:- Step 1: open the report, print summary + findings
- Step 2: per-finding interactive triage (accept / reject / defer / false-positive)
- Step 3: apply accepted diffs (bottom-to-top within a file)
- Step 4: update the run entry + aggregate precision metrics in
_state.md - Step 5: propose the batch commit — wait for the principal's explicit go
- Step 6: shadow-mode promotion gate check (only after
shadow_mode_end_date)
- No auto-commit. The commit in Step 5 happens only on the principal's confirmation.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 82 lines · 44 tokens per session scan A 963a642c5b0a
consistency-review is a skill published in the GitHub repository jaroslavsoucek-art/Giovanni (2 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 1,309 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-17.
Other skills, from other repositories
github-project-management
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning.
V3 Swarm Coordination
15-agent hierarchical mesh coordination for v3 implementation. Orchestrates parallel execution across security, core, and integration domains following 10 ADRs with 14-week timeline.
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
bazel-build-optimization
Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.
track-management
Use this skill when creating, managing, or working with Conductor tracks - the logical work units for features, bugs, and refactors. Applies to spec.md, plan.md, and track lifecycle operations.
taskmarket-delegate
Delegate work to the TaskMarket agent-worker market - browse open tasks, create tasks with explicit authorization, and track/submit work, so an agent can outsource instead of burning inference on unreliable or low-confidence work.