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 skills add alonf/specrew --skill three-gate-drift-detectiongit clone --depth 1 https://github.com/alonf/specrewWrote 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/skills/alonf/specrew/three-gate-drift-detection)<a href="https://agentmods.dev/skills/alonf/specrew/three-gate-drift-detection"><img src="https://agentmods.dev/badge/skills/alonf/specrew/three-gate-drift-detection/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/skills/alonf/specrew/three-gate-drift-detection"><img src="https://agentmods.dev/badge/skills/alonf/specrew/three-gate-drift-detection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00037 | $0.01944 |
| Opus 5.5 | $0.00015 | $0.00778 |
| Sonnet 5.5 | $0.00007 | $0.00389 |
| Haiku 4.5 | $0.00004 | $0.00194 |
Grade A, and why
three-gate-drift-detection 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 1mo 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
Iteration 002 demonstrated that specification and implementation drift can be reliably caught and resolved within the same iteration using three synchronized gates, with zero rework loops required. The pattern emerged from:
- Planning gate (validate-governance.ps1): Enforces effort-model alignment, capacity checks, traceability validation
- Spec review gate (Spec Steward audit): Catches implementation drift vs. requirement intent early by auditing planned tasks
- Reviewer verdict gate (per-requirement slice acceptance): Binds specification compliance with test coverage and acceptance criteria verification
All three gates operate in parallel (not serial), and each gate focuses on a distinct class of drift:
- Planning gate: Structural alignment (capacity, traceability, metadata)
- Spec review gate: Specification ambiguity (acceptance criteria, implicit dependencies)
- Reviewer gate: Implementation fidelity (spec compliance, test coverage, acceptance pass)
Pattern
Gate 1: Planning Gate (Pre-Execution)
- When: Before the iteration moves from
planningtoexecutingstatus - Who: Planner + validator automation
- What to check:
- All tasks have requirement references (FR/TG mappings)
- Total estimated effort does not exceed capacity or overcommit threshold
- Effort model snapshot is present and matches
.specrew/iteration-config.yml - Phase-level estimation baseline is documented
- Failure path: If validation fails, add a clarification task or defer requirement; re-plan and re-validate
- Success criteria: Validator exits cleanly; all tasks pass traceability and capacity checks
Gate 2: Spec Review Gate (During Planning Ceremony)
- When: During planning ceremony, as part of task review (pre-execution, same timing as Gate 1)
- Who: Spec Steward (in parallel with implementers preparing task designs)
- What to check:
- Does the spec define all acceptance criteria for each planned task?
- Are there implicit dependencies or hidden couplings between tasks?
- Is the success condition binary (pass/fail) or subjective?
- Are there ambiguities in language, scope, or priority?
- Failure path: If gaps are found, add clarification tasks to this iteration or defer requirement; re-plan before execution
- Success criteria: Spec Steward confirms each task's requirement is unambiguous and implementable
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.
- 1mo ago First seen · 153 lines · 37 tokens per session scan A 34f150e77e78
three-gate-drift-detection is a skill published in the GitHub repository alonf/specrew (55 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 1,944 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
team-qa
Orchestrate the QA team through a full testing cycle — qa-lead strategy and test plan, qa-tester case writing, execution, sign-off.
scaffold-dotnet-test-project
MUST USE when an existing .NET test project was excluded from a .slnf/CI solution filter, disappeared from .sln/.slnx discovery, or lost its production ProjectReference; also for requests to set up, create, reuse, add, register, include, or repair a test project. Handles "tests pass directly but CI discovers zero"…
conductor-implement
Execute tasks from a track's implementation plan following TDD workflow.
test-result-feedback
Close the acceptance loop for a tested change — consume the apc test TierResult, map EACH acceptance criterion to a pass/fail outcome from structured fields (never chat text), attach an evidence ref, and write it back to the task. A SUT red is a finding, never softened to green.
cy-execute-task
Implement and verify an existing CompozyOS spec task, then update its tracking. Excludes review remediation.
implement-feature
Implement an approved feature plan with fresh-context slices, TDD, revision-bound evidence, and PR-ready output.