agentmods.dev

consistency-check

consistency-check is a skill for Claude Code from jaroslavsoucek-art/Giovanni. It costs 52 tokens per session (1,968 once invoked), scanned A, original, MIT.

A read-only check for meaning conflicts across project memory, rules, decisions, agent descriptions, linked documents, and published pages. It proposes changes but does not apply them.

In plain words
What is it for?
Use it to check all enabled consistency rules, run one named check, limit staleness checks to a time window, and record the findings.
Why use it?
Automated file checks can confirm syntax while missing documents that disagree or links and decisions that have become outdated. This finds those cross-document inconsistencies.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the giovanni plugin — 11 skills, 1 command, 9 agents, 4 hooks shipped together

not rated 2repo yesterday A scan 52 tokens original MIT

Good fit Use it to check all enabled consistency rules, run one named check, limit staleness checks to a time window, and record the findings.

Compare 6 skills from other repositories ↓
View source ↗ jaroslavsoucek-art/Giovanni
Install

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.

Claude Code
/plugin marketplace add jaroslavsoucek-art/Giovanni
Claude Code
/plugin install giovanni

Made for: Claude Code.

Or install giovanni, the plugin that ships this one along with the rest of its 11 skills, 1 command, 9 agents, 4 hooks.

Wrote 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.

agentmods badge for consistency-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/jaroslavsoucek-art/giovanni/consistency-check/github.svg)](https://agentmods.dev/skills/jaroslavsoucek-art/giovanni/consistency-check)
Your own site
<a href="https://agentmods.dev/skills/jaroslavsoucek-art/giovanni/consistency-check"><img src="https://agentmods.dev/badge/skills/jaroslavsoucek-art/giovanni/consistency-check/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.

agentmods 80×15 button for consistency-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/jaroslavsoucek-art/giovanni/consistency-check"><img src="https://agentmods.dev/badge/skills/jaroslavsoucek-art/giovanni/consistency-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,968 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00052 $0.01968
Opus 5.5 $0.00021 $0.00787
Sonnet 5.5 $0.00010 $0.00394
Haiku 4.5 $0.00005 $0.00197

Measured today against content hash 04a3b95ba978, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

consistency-check 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.

plugin/skills/consistency-check/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/giovanni:consistency-check

Run the 8 semantic invariants that deterministic ${CLAUDE_PLUGIN_ROOT}/scripts/lint.sh cannot reach (memory↔constitution drift, decisions↔constitution drift, agent roster description mismatch, topic shard cross-reference breakage, optional architecture audit staleness, decided-terms completeness, knowledge↔knowledge cross-doc drift, published-pages outbound drift). This command is a thin shell — checks and report format live in the giovanni:consistency-checker agent. This file is the invocation contract.

Usage

/giovanni:consistency-check                          # all enabled checks
/giovanni:consistency-check --check <id>             # single check
/giovanni:consistency-check --since <YYYY-MM-DD>     # narrows git-log scan window for staleness checks
/giovanni:consistency-check --write                  # commit findings to file (default = also writes; flag is reserved for future render-only mode)

Valid --check ids:

  • memory-blockers-vs-constitution
  • decisions-vs-constitution
  • agent-roster-semantic
  • topic-shard-stakeholder-xref
  • audit-staleness (optional — only if fork uses architecture tier audits)
  • decided-terms-completeness (no-op with INFO if memory/audits/consistency/decided-terms.yaml is absent)

Argument syntax

Arg Type Default Meaning
--check <id> parameterized all Run a single check by ID instead of all enabled checks.
--since <YYYY-MM-DD> parameterized date 30 days ago For staleness check (audit-staleness): limits the git-log window. Ignored by other checks.
--write boolean flag implicit (always writes report) Reserved for future render-only mode. Default behavior writes the report file.

Pre-flight (binding — STOP on failure)

Before spawning giovanni:consistency-checker:

  1. CWD check. Working directory is a Giovanni repo (presence of memory/CLAUDE_MEMORY.md + knowledge/<constitution>.md). Otherwise STOP.
  2. Agent definition present. ${CLAUDE_PLUGIN_ROOT}/agents/consistency-checker.md exists. Missing → STOP.
  3. Audit directory present. memory/audits/consistency/ exists. Create if missing (this is the only directory the orchestrator creates pre-spawn).
  4. State file present. memory/audits/consistency/_state.md exists with a non-empty shadow_mode_start_date field. If missing or empty:
    • Auto-seed: set shadow_mode_start_date = today, shadow_mode_end_date = today + 28 days.
    • Surface advisory: INFO: seeded shadow mode 28d from today. Score precision before promoting to operational warnings.
  5. Constitution + L1 present. knowledge/<constitution_file>.md (per docs/governance.config.yaml) and memory/CLAUDE_MEMORY.md exist. Missing → STOP — the checks have no input.

Read the full file on GitHub · 120 lines

Changes

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.

  1. today First seen · 120 lines · 52 tokens per session scan A 04a3b95ba978

Subscribe to this mod's changes

consistency-check is a skill published in the GitHub repository jaroslavsoucek-art/Giovanni (2 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 1,968 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.

Debuggingagent-frameworkagentic-aiai-agentsanthropicchief-of-staff
Related

Other skills, from other repositories

continuum-observability

Trace agent runs with Langfuse, decorate functions with @observe, collect latency/token/error metrics, and report errors. Invoke when the user asks about "see what the LLM was prompted with", "Langfuse traces", "track latency", "metrics dashboard", "error reporting", or "instrument my function".

shyftlabs/continuum · 70 tokens

Debug Snapshot

Capture the host's environment, working directory, recent git activity, and pipeline-relevant state so you can diagnose "what's actually happening on the machine".

CocoRoF/geny-executor · 34 tokens

python-code-quality

Code quality checks, linting, formatting, and type checking commands for the Agent Framework Python codebase. Use this when running checks, fixing lint errors, or troubleshooting CI failures.

microsoft/agent-framework · 40 tokens

triage-issue

Analyze a GitHub issue, verify claims against the codebase, and close invalid issues with a technical response.

aden-hive/hive · 0 tokens

hive.error-recovery

Follow a structured recovery decision tree when tool calls fail instead of blindly retrying or giving up.

aden-hive/hive · 25 tokens

skill-repair

Diagnose and fix failing or degraded skills automatically - systemic-first triage, per-category playbooks, and a verification plan.

aeonfun/aeon · 28 tokens