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/danielvm-git/bigpowers/gate-tracegit clone --depth 1 https://github.com/danielvm-git/bigpowersWrote 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/danielvm-git/bigpowers/gate-trace)<a href="https://agentmods.dev/rules/danielvm-git/bigpowers/gate-trace"><img src="https://agentmods.dev/badge/rules/danielvm-git/bigpowers/gate-trace.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 | $0.00050 | $0.01106 |
| Opus 5 | $0.00025 | $0.00553 |
| Sonnet 5 | $0.00010 | $0.00221 |
| Haiku 4.5 | $0.00005 | $0.00111 |
Grade A, and why
gate-trace 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 today.
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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gate Trace
Deterministic quality gate that combines traceability coverage and blind-spot data into a single PASS/FAIL/CONCERNS/WAIVED decision before release.
Decision Rules
| Rule | Condition | Verdict |
|---|---|---|
| R1 | Any undone story with 0 code tags | FAIL |
| R2 | Any story done but no verify evidence | CONCERNS |
| R3 | P0 story (top WSJF quartile) with 0% coverage | FAIL |
| R4 | Overall coverage < 60% | CONCERNS |
| R6 | P0 story + eNN-TEST_PLAN_LATEST.md exists + zero SC-eNNsYY-P0-* in test files | CONCERNS |
| R5 | Overall ≥ 80% + no critical gaps + all verify → PASS | PASS |
Oracle Confidence Downgrade
TEA-inspired: if trace links rely on heuristics rather than explicit tags, confidence drops.
| Heuristic Ratio | Downgrade |
|---|---|
| > 50% links from heuristics (file-name or task-reference) | One level (PASS→CONCERNS, CONCERNS→FAIL) |
| > 80% links from heuristics | Two levels (PASS→FAIL, CONCERNS→FAIL) |
Process
- Pre-flight: Ensure
scripts/trace-stories.sh --jsonhas been run (producesspecs/traceability-matrix.json). If not present, run it. - Ensure
scripts/check-blind-spots.shhas been run (producesspecs/blind-spots.json). If not present, run it. - Read
specs/traceability-matrix.jsonandspecs/blind-spots.json. - Apply decision rules R1–R5 in order (first match wins).
- Apply oracle confidence downgrade based on the heuristic link ratio from the matrix's
oracle_stats. - Drift check (e39s03): If
specs/drift-report.jsonexists and has suspect links, mark verdict as CONCERNS with note: "Drift detected — some implementing files are newer than their specs. Run scripts/check-spec-drift.sh for details." - Output verdict + rationale to stdout.
- Adversarial refute check (e45s32): Before emitting PASS, attempt to refute the verdict — list at least one concrete traceability gap that would block merge if it were real. If the gap is real, downgrade the verdict. Rubber-stamping is prohibited; every PASS must survive one refutation attempt.
- Completeness critic (e45s05) — Run adversarial gap-finding:
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.
- today First seen · 92 lines · 50 tokens per session scan A c712b007cfb7
gate-trace is a cursor rule published in the GitHub repository danielvm-git/bigpowers (163 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 1,106 once invoked, about $0.0003 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 2026-09-03.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
app-router-patterns
Next.js 14+ App Router patterns — Server Components, Client Components, Route Handlers, Server Actions, and metadata API.
00-project-rules
ContextOS core project rules and role orchestration.
context-os
ContextOS rules for context-os.
database
Database architecture, schema design, Prisma, Drizzle ORM, indexing strategies, migrations, and N+1 query resolution.
vue
Rules for Vue (2 and 3) single-file components.