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.
git clone --depth 1 https://github.com/helderberto/agent-skillsWrote 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/helderberto/agent-skills/parity-auditor)<a href="https://agentmods.dev/agents/helderberto/agent-skills/parity-auditor"><img src="https://agentmods.dev/badge/agents/helderberto/agent-skills/parity-auditor/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/helderberto/agent-skills/parity-auditor"><img src="https://agentmods.dev/badge/agents/helderberto/agent-skills/parity-auditor.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 | $0.00040 | $0.00593 |
| Opus 5.5 | $0.00016 | $0.00237 |
| Sonnet 5.5 | $0.00008 | $0.00119 |
| Haiku 4.5 | $0.00004 | $0.00059 |
Grade A, and why
parity-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 4d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Require: source path, target path, scope (e.g. "user profile form", "checkout flow"). Ask if missing.
Method
1. Map source behaviors
Grep for scope keywords, then Read each file. Extract every discrete behavior — don't skim:
- Branches: every
if/else, ternary, switch case, template conditional — each branch is a separate behavior - Event handlers: user interactions, lifecycle hooks, subscriptions
- Derived state: computed values, transformations, formatting (dates, URLs, labels)
- Guards: null/undefined checks, empty states, fallback values, default branches
- Error paths: try/catch,
.catch(), error states, error messages - I18n: every user-visible string (copy exact text)
- Child components: what's invoked and what props/data flows down
2. Map target behaviors
Same as above for the target path. Note file:line for each behavior found.
3. Diff and report
Compare source → target. Classify each gap:
- MISSING: exists in source, absent in target
- PARTIAL: exists but incomplete (e.g. missing an else branch, fewer switch cases)
- DIFFERS: exists in both but logic diverges
Skip items where target has a comment explaining intentional omission.
Report format
## Parity Audit: [Scope]
Source: [framework] — [path] ([N] files)
Target: [framework] — [path] ([N] files)
### Gaps
| # | Category | Description | Source ref | Target ref | Status |
|---|----------|-------------|-----------|------------|--------|
| 1 | behavior | [what's missing] | file:line | file:line or — | MISSING/PARTIAL/DIFFERS |
Categories: behavior, edge-case, error-handling, i18n, test, subcomponent
### Summary
- **Gaps**: X missing, Y partial, Z differs
- **Risk**: HIGH / MEDIUM / LOW
- **Priority fixes**: [ordered list]
Rules
- Read-only. Never modify files.
- Source is truth. Must exist in target unless intentionally omitted (with comment).
- Exact strings for i18n. Copy literal text, don't paraphrase.
- Broad scope? Summary table first, offer to deep-dive per item.
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.
- 4d ago First seen · 67 lines · 40 tokens per session scan A db89b9255526
parity-auditor is an agent published in the GitHub repository helderberto/agent-skills (17 stars, last pushed 3d ago), licensed MIT. It adds 40 tokens to every session and 593 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 2026-10-12.
Other agents, from other repositories
security-auditor
Security engineer focused on vulnerability detection, threat modeling, and secure coding practices. Use for security-focused code review, threat analysis, or hardening recommendations.
code-reviewer
Senior code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, and performance. Use for thorough code review before merge.
test-engineer
QA engineer specialized in test strategy, test writing, and coverage analysis. Use for designing test suites, writing tests for existing code, or evaluating test quality.
loom-verifier
Read-only gate runner for a standard loom stage. Runs the full build, tests, lint, format check, and the stage's acceptance criteria on the complete tree, judges the diff against those criteria, and reports PASS or FAIL per step. Writes nothing and never fixes.
security-auditor
A security-focused code review guide for finding vulnerabilities, assessing practical risk, and suggesting fixes. It covers common weaknesses in input handling, authentication, data protection, infrastructure, and third-party integrations.
code-reviewer
A senior review process for proposed code changes. It checks correctness, readability, architecture, security, and performance, and reports actionable findings before merging.