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 rules/alphabitcore/nexus-gateway/completion-time-self-auditgit clone --depth 1 https://github.com/AlphaBitCore/nexus-gatewayWrote 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/rules/alphabitcore/nexus-gateway/completion-time-self-audit)<a href="https://agentmods.dev/rules/alphabitcore/nexus-gateway/completion-time-self-audit"><img src="https://agentmods.dev/badge/rules/alphabitcore/nexus-gateway/completion-time-self-audit.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 | $0.01203 | $0.01203 |
| Opus 5 | $0.00602 | $0.00602 |
| Sonnet 5 | $0.00241 | $0.00241 |
| Haiku 4.5 | $0.00120 | $0.00120 |
Grade A, and why
completion-time-self-audit 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 5d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Completion-time self-audit — 2+ rounds (binding)
Before saying "done" / asking the user to commit / closing out a task, you MUST run a short self-audit and report the result back in the response. This rule is the safety net against silent "almost done" deliveries.
Minimum two rounds (per CLAUDE.md "Post-plan 2-round self-review"):
- Round 1 — run the 4-question audit. Surface every issue. For each issue: fix it now, OR capture as a follow-up todo with stated reason.
- Round 2 — re-run the same 4 questions. Verify each round-1 fix actually closed the gap. Check that nothing new appeared from the fixes.
- More rounds if round 2 finds new issues — keep iterating until TWO consecutive rounds are clean.
Catching issues is cheap; verifying you actually fixed them is what makes "done" real. A single audit that surfaces N issues and a quick "all fixed" claim is not enough — only the second clean round confirms the fixes stuck.
The 4-question self-audit
Answer all four with concrete evidence (file paths, grep output, test names):
1. Anything deferred?
Did I split scope and leave a part for "later"? Possible signals:
- A todo I marked
completedwhose work was only partially done. - A spec section I implemented to "half" depth.
- A subsystem I planned to touch but didn't.
If any item was deferred:
- It must be a separate, explicit todo in the active list (not silently dropped).
- The user must be told about it in the response.
- It must NOT be marked complete.
2. Any TODO / FIXME / XXX left in production code?
git diff HEAD~1.. --stat # files changed
git diff HEAD~1.. | grep -nE 'TODO|FIXME|XXX' | head -50 # new markers in changes
In production / runtime code paths these are forbidden as substitutes for real behaviour (binding in CLAUDE.md). Exceptions:
- Test code (
*_test.go,*.test.ts,*.spec.ts). - Truly auto-generated files marked with a header like
Code generated by … DO NOT EDIT.(the repo currently has no active generator;packages/shared/schemas/configtypes/is hand-maintained — the exception stands in case a future generator is added). - Pre-existing markers you didn't add this turn.
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.
- 5d ago First seen · 100 lines · 1,203 tokens per session scan A d491e0b15687
completion-time-self-audit is a cursor rule published in the GitHub repository AlphaBitCore/nexus-gateway (23 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,203 tokens to every session, about $0.0060 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 cursor rules, from other repositories
10-deterministic-audit
Enforce deterministic audit behavior — no invented controls, cite authoritative sources, emit traceable artifacts.
flagship_author
How to author a flagship in ks-cookbook.
recipe_author
How to author a recipe in ks-cookbook.
30-framework-routing
Route tasks to HIPAA, HITECH, PCI-DSS, SOC 2, ISO 27001, NIST CSF, NIST AI RMF, FERPA, COPPA, CCPA, US state privacy, GDPR, FedRAMP, SOX, CMMC, and GLBA skills based on user intent and presets.
00-compliance-agent-core
Core compliance agent mission, PHI redaction gate, and audit lifecycle for HIPAA, PCI-DSS, and SOC 2.
20-phi-redaction-first
PHI redaction first — Presidio gate, token handling, and minimum necessary LLM access for HIPAA workflows.