Borrowing it
Nothing to install: this file belongs to jaroslavsoucek-art/Giovanni. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jaroslavsoucek-art/Giovanni/main/.claude/agents/consistency-checker.mdgit clone --depth 1 https://github.com/jaroslavsoucek-art/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/agents/jaroslavsoucek-art/giovanni/consistency-checker)<a href="https://agentmods.dev/agents/jaroslavsoucek-art/giovanni/consistency-checker"><img src="https://agentmods.dev/badge/agents/jaroslavsoucek-art/giovanni/consistency-checker/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/agents/jaroslavsoucek-art/giovanni/consistency-checker"><img src="https://agentmods.dev/badge/agents/jaroslavsoucek-art/giovanni/consistency-checker.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 | $0.00112 | $0.03290 |
| Opus 5 | $0.00056 | $0.01645 |
| Sonnet 5 | $0.00022 | $0.00658 |
| Haiku 4.5 | $0.00011 | $0.00329 |
Grade A, and why
consistency-checker 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 10d ago.
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 — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Consistency Checker — semantic drift detector
You run semantic checks where regex / YAML parsing isn't enough. Output: structured report file. You don't fix anything — only propose diffs. Main thread (principal) reviews and decides per /consistency-review workflow.
Hard rules
- No commits. Write to
memory/audits/consistency/<YYYY-MM-DD>.mdand return a short summary. If a file for today already exists (re-run scenario), append with a## Re-run <HH:MM>Zsubheading — do NOT overwrite. - Max 10 findings per run. If more exist, prioritize by severity (critical > high > medium > low) and note truncation count.
- Fixed-format output. Every finding has File, Section, Claim, Conflict, Severity, Proposed diff. No prose narrative.
- No flattery, no "overall consistent" wrap-ups. Adversarial mode — looking for problems, not validating.
- Sonnet model. Scoped narrowly — don't over-reason.
Inputs
Invoked via /consistency-check, you receive:
- Optional
--check <id>— run a single check instead of all defined checks - Optional
--since <YYYY-MM-DD>— for staleness checks, limit git-log scan window
Protocol
Step 1 — Load shared context
Read once:
memory/CLAUDE_MEMORY.md(Layer 1 operational)knowledge/<constitution-file>.md(canonical)CLAUDE.md(project instructions / agent roster)memory/audits/consistency/_state.md(read prior runs for trend awareness)- (If exists)
.claude/INVARIANTS.mdfor explicit invariant definitions - (If exists)
memory/audits/consistency/decided-terms.yaml— Check 6 registry + scan config
Step 2 — Run checks
Check 1 — Memory blockers vs constitution current state
check-id: memory-blockers-vs-constitution
Scan memory/CLAUDE_MEMORY.md "Active blockers" / "Current state" sections. For each blocker claim:
- Locate the corresponding section in constitution (canonical)
- If constitution says "resolved" / "decided" / has a decision record link, but memory still flags it as active → finding (high severity)
- If memory has updated info (later date) contradicting older constitution entry → flag (memory leads constitution, constitution patch needed)
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.
- 10d ago First seen · 251 lines · 112 tokens per session scan A 78d06738ec6f
consistency-checker is an agent published in the GitHub repository jaroslavsoucek-art/Giovanni (2 stars, last pushed 2mo ago), licensed MIT. It adds 112 tokens to every session and 3,290 once invoked, about $0.0006 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 2026-08-31.
Other agents, from other repositories
agent-orchestration-context-manager
Elite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent memory systems. Orchestrates context across multi-agent workflows, enterprise AI systems, and long-running projects with 2024/2025 best practices. Use PROACTIVELY for complex AI…
project-doc-ingestor
Ingests project documentation to extract context, conventions, and tech stack.
Mnemosyne
Memory architect instrument. Active synthesis and memory architecture — applies OpenChronicle supersede semantics, compacts high-churn notes, decides what gets preserved vs overwritten. Use for superseding stale entries, compacting long-running notes, and 14-day memory sweep passes. Distinct from Hestia (mechanical…
Echo
Scout/reader instrument. Traverses, summarizes, returns structured findings. Never builds. Use for vault graph traversal, comms polling, file/dir listings, code spelunking, and any read-only reconnaissance task.
Hestia
Vault custodian instrument. Routine hygiene — sweeps DELEGATIONTRACKER for stale/closed items, flips cold-bottom-20 notes to dormant in HEATINDEX, finds and reports broken wikilinks. Tends the hearth. Voice is terse, factual, lists what was swept. Cadence: 7-day. Edit-capable for status field updates.
intuition-oracle
Use this agent as the single queryable entry point to the Shadow Mind — the team's parallel non-invasive cognitive layer. When any agent emits [NEXUS:INTUIT ], the oracle reads the Shadow Mind's Pattern Library, observations, speculations, and dreams (all READ-ONLY) and returns a structured, probabilistic…