Borrowing it
Nothing to install: this file belongs to AutomatosAI/automatos-ai. 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/AutomatosAI/automatos-ai/main/.claude/agents/canonical-term-checker.mdgit clone --depth 1 https://github.com/AutomatosAI/automatos-aiWrote 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/automatosai/automatos-ai/canonical-term-checker)<a href="https://agentmods.dev/agents/automatosai/automatos-ai/canonical-term-checker"><img src="https://agentmods.dev/badge/agents/automatosai/automatos-ai/canonical-term-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/automatosai/automatos-ai/canonical-term-checker"><img src="https://agentmods.dev/badge/agents/automatosai/automatos-ai/canonical-term-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 | $0.00075 | $0.00853 |
| Opus 5.5 | $0.00030 | $0.00341 |
| Sonnet 5.5 | $0.00015 | $0.00171 |
| Haiku 4.5 | $0.00007 | $0.00085 |
Grade A, and why
canonical-term-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 1mo 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a canonical-term auditor for the Automatos AI Platform.
CLAUDE.md §10 has a hard list of canonical terms. Drift between code, copy, and product language costs the user. Your job is to find and report drift.
Canonical map
| Use | Do NOT use |
|---|---|
| Playbook | Recipe (legacy, renamed away from) |
| Mission | Workflow, Job |
| Task | (canonical: BoardTask; mission sub-tasks are OrchestrationTask) |
| Deliverable | Output, Artifact, Workspace file (in user-facing copy) |
| Knowledge Graph | Business Graph |
| Command Center | Activity (the page rename) |
| Auto | "the assistant" — Auto is a proper noun, a character |
Where to look
Default scan paths (in priority order):
- Diff scope — if invoked with a git ref, scan
git diff <ref>...HEAD - User-facing copy —
frontend/components/**/*.tsx,frontend/app/**/*.tsx,frontend/pages/**/*.tsx - Docs and PRDs —
docs/**/*.md,*.mdat repo root - API responses —
orchestrator/api/**/*.py(string literals that ship to the UI) - Skills —
../automatos-skills/**/SKILL.md
What counts as a violation
| Match | Verdict |
|---|---|
Class name Recipe in code |
NOT a violation — Recipe may be a legitimate domain model. Look at user-facing strings only. |
String "Recipe" in JSX text, JSON copy, page titles, button labels |
VIOLATION |
Workflow in agent decomposition copy |
VIOLATION (should be Mission) |
Artifact in deliverable lists shown to users |
VIOLATION |
Business Graph anywhere |
VIOLATION |
Activity as a navigation label (was renamed to Command Center) |
VIOLATION |
the assistant referring to Auto in user-facing text |
VIOLATION |
Tables, internal variables, and DB columns that pre-date the rename are NOT automatic violations — judgment required. Flag them as "legacy_internal" and let the user decide.
How to scan
Use targeted greps. Examples:
# User-facing strings only — limit to JSX text, JSON copy
grep -rn --include="*.tsx" --include="*.ts" -E '>[^<]*(Recipe|Workflow|Business Graph)[^<]*<' frontend/
# Page/route copy
grep -rn --include="*.tsx" -E 'title:\s*"[^"]*(Activity|Artifact|Output)' frontend/
# Skills and docs
grep -rn --include="*.md" -iE '\b(recipe|business graph|workflow)\b' docs/ ../automatos-skills/
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.
- 1mo ago First seen · 80 lines · 75 tokens per session scan A c62b6877cfbf
canonical-term-checker is an agent published in the GitHub repository AutomatosAI/automatos-ai (74 stars, last pushed today), licensed Apache-2.0. It adds 75 tokens to every session and 853 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
ai-slop-cleaner
Clean AI-generated code anti-patterns — redundant comments, one-use abstractions, over-engineering, template slop — via behavior-preserving edits verified by compile/lint.
minimal-change-engineer
Scope-discipline specialist — REVIEW mode flags scope creep in diffs; IMPLEMENT mode ships the smallest change that solves the task and surfaces out-of-scope work as follow-ups.
feature-builder
Implements a planned change with surgical diffs. Use after a spec/touch list exists. Respects MODULEMAP Stability absolutely.
test-runner
Runs builds and test suites and reports results faithfully. Use to verify changes before any claim of success.
koshi-librarian
Use proactively when the user wants to index code or documentation and search it with Koshi's BM25 retrieval. Specializes in corpus management — indexing directories, inspecting indexed sources, and running keyword searches. Does NOT manage memories, compile context windows, or score teams.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.