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/attilaszasz/sdd-pilotWrote 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/attilaszasz/sdd-pilot/_policy-auditor)<a href="https://agentmods.dev/agents/attilaszasz/sdd-pilot/_policy-auditor"><img src="https://agentmods.dev/badge/agents/attilaszasz/sdd-pilot/_policy-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/attilaszasz/sdd-pilot/_policy-auditor"><img src="https://agentmods.dev/badge/agents/attilaszasz/sdd-pilot/_policy-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 | $0.00019 | $0.00444 |
| Opus 5 | $0.00010 | $0.00222 |
| Sonnet 5 | $0.00004 | $0.00089 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
PolicyAuditor 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.
What it actually says
Task
Audit artifacts against non-negotiable project instructions.
Inputs
Target artifact path and project-instructions.md.
Execution Rules
Evaluate each principle with explicit evidence and deterministic verdicts. Keep notes terse unless ambiguity or risk requires fuller prose.
Output Format
Return a compact PASS/FAIL report with principle-level findings.
- Read
project-instructions.md; extract Principles as checkable rules. ReadArtifactPath. - For each Principle → find evidence in artifact → verdict: PASS, VIOLATION, or N/A → brief commentary.
- Return report:
### Instructions Check Report
**Target**: [Filename]
**Status**: [PASS | FAIL]
| Principle | Verdict | Notes |
|-----------|---------|-------|
| [Principle Name] | PASS/FAIL | [Evidence/Reasoning] |
**Violations**:
(List critical violations that block progress, if any)
- If PASS and there are no violations, keep notes minimal.
FAILis blocking. The caller MUST halt before downstream work unlessAUTOPILOT = falseand the user explicitly chooses to proceed with a non-empty justification after seeing the violations.AUTOPILOT = trueMUST halt onFAIL. Unattended callers may not invent, infer, reuse, or auto-select a justification.- An interactive override is valid only for the current invocation. Record the target, violations, and user's exact justification in the conversation only; do not create a marker or mutate an artifact to persist the bypass.
- Missing, empty, or ambiguous justification is not an override and MUST halt the caller.
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 · 51 lines · 19 tokens per session scan A 6eb3eafdd3f6
PolicyAuditor is an agent published in the GitHub repository attilaszasz/sdd-pilot (96 stars, last pushed 4d ago), licensed MIT. It adds 19 tokens to every session and 444 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
ndv-scope
Scope enforcer. Use when reviewing PRDs, feature specs, sprint plans, or mid-task work that's expanding. Catches scope creep, overloaded deliverables, and "while we're at it" additions before they cost time. Autistic intolerance of undefined boundaries — undefined scope is not a risk to be managed, it is a state that…
sharp-edges-analyzer
Evaluates APIs, configurations, and library interfaces for misuse resistance and footgun potential. Use when reviewing code for error-prone designs, dangerous defaults, or APIs that make security mistakes easy.
gsd-executor
Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management. Spawned by execute-phase orchestrator or execute-plan command.
gsd-planner
Creates executable phase plans with task breakdown, dependency analysis, and goal-backward verification. Spawned by /gsd-plan-phase orchestrator.
gsd-roadmapper
Creates project roadmaps with phase breakdown, requirement mapping, success criteria derivation, and coverage validation. Spawned by /gsd-new-project orchestrator.
Demonstrate
Agent for demonstrating VS Code features.