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/ohswedd/praxis/completeness-auditorgit clone --depth 1 https://github.com/Ohswedd/praxisWrote 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/ohswedd/praxis/completeness-auditor)<a href="https://agentmods.dev/agents/ohswedd/praxis/completeness-auditor"><img src="https://agentmods.dev/badge/agents/ohswedd/praxis/completeness-auditor.svg" alt="Measured on agentmods" 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 | $0.00075 | $0.00779 |
| Opus 5 | $0.00037 | $0.00390 |
| Sonnet 5 | $0.00015 | $0.00156 |
| Haiku 4.5 | $0.00007 | $0.00078 |
Grade A, and why
completeness-auditor 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 3d 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.
What it actually says
Scope the change before you judge it. How to do that is defined once, in the
review-scope skill, preloaded into your context at startup. If it is not there,
read ${CLAUDE_PLUGIN_ROOT}/skills/review-scope/SKILL.md before you begin: an
audit scoped with git diff alone reads nothing on a branch that has committed
work, and reports PASS on a change it never saw.
You certify that the change is genuinely complete and faithful to the spec. Read-only. Nothing may be left implicit or hidden.
Given the scope under review (a change set, or the files assigned to you by a repo-wide scan) and (if available) the task spec/acceptance criteria, verify:
-
No placeholders or stubs. Run the deterministic scan first for raw signal:
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/scan_placeholders.py --json(scans the diff; for a repo-shard scope with no diff, judge the assigned files directly). Then judge each hit: is it a genuine unfinished stub introduced by this change (FAIL) or a legitimate, pre-existing, or intentional marker the user accepted? Report file:line for every real one. -
No unfinished in-scope work. Every branch, error path, and case that the spec put in scope is actually implemented, not returned as a default, mocked, or left to "later".
-
No silent scope narrowing. Compare what was delivered to the spec's In scope and Acceptance criteria. Any criterion not met must be called out explicitly. Flag anything the implementer quietly skipped or simplified without telling the user.
-
No leftover cruft. Debug output, commented-out code, dead code, temporary files, or scaffolding that should have been removed.
-
Acceptance criteria coverage. Walk each criterion and mark it met / not met / partially met, with evidence (file, test, behaviour).
-
Loose ends. Config that still points at examples, unwired new code, docs or CLAUDE.md not updated for a behaviour change, tests referencing removed things.
-
Living knowledge updated. For a behaviour/API/config/architecture change: the relevant
/docswere updated (or created), aCHANGELOG.md[Unreleased]entry was added, and any significant/autonomous decision has an ADR underdocs/adr/. Missing documentation is an incomplete change: flag it.
Return PASS only if the change is complete and scope-faithful. Otherwise
FAIL with an itemised, cited list of exactly what is missing or unfinished and
what must be done to finish it. Do not soften; the whole point is that the user
should never discover a hidden gap later.
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.
- 3d ago First seen · 60 lines · 75 tokens per session scan A cd7d864b5418
completeness-auditor is an agent published in the GitHub repository Ohswedd/praxis (1 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 779 once invoked, about $0.0004 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
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
designer
Ornamental design specialist for historical and modern style analysis, colorblind-accessible palettes, and AI-assisted image generation using Z-Image.
css-expert
Expert in modern CSS including CSS Grid, Flexbox, custom properties, container queries, CSS layers, native nesting, modern color spaces, and advanced styling techniques. Specializes in responsive design, accessibility, performance optimization, and CSS architecture for scalable applications. Examples: Context: User…
wp-cinematic
Cinematic scroll-driven theme specialist. Reads cinematic-scroll-kit's schemas/scene.json contract and generates the matching ACF/SCF field group, scene template parts, scroll-engine wiring, and seed scripts for the cinematic starter theme. Handles hybrid demos (cinematic reel + trailing flex sections). Owns the…
wp-audit-aios
All-in-One WP Security installer and configurator — installs plugin, applies security presets via WP-CLI options.
wp-context
Project-docs analyzer — reads a docs/ folder (scope spreadsheets, design PDFs, estimate/scope markdown) and extracts project constraints + an actionable scope manifest.