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 skills/orin-dx/agent-plugins/gatenpx skills add orin-dx/agent-plugins --skill gategit clone --depth 1 https://github.com/orin-dx/agent-pluginsWhat 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 | $0.00143 | $0.00716 |
| Opus 5 | $0.00072 | $0.00358 |
| Sonnet 5 | $0.00029 | $0.00143 |
| Haiku 4.5 | $0.00014 | $0.00072 |
Grade A, and why
gate 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 2d 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
Sentinel Gate Skill
<when_to_activate>
Activate on any of these signals:
- Explicit gate request: "verify", "gate", "is this done?", "does this meet criteria?", "quality check"
- Stage transition: about to start implementation → gate the spec; about to open PR → gate the implementation
- Artifact type matches: requirement, spec, plan, implementation, PR
Do not activate for: general code questions, exploratory research, or authoring tasks where no artifact boundary is being crossed.
</when_to_activate>
<three_stage_flow>
One skill, one three-agent pipeline, reused against whatever artifact type it's handed — requirement, spec, plan, implementation, PR, changeset, finding-report. recon's job is exactly to work out what it's looking at and what criteria apply, so the same chain runs unchanged regardless of artifact type — there is no separate sub-skill or agent set per type.
| Stage | Agent | Model | Effort | Responsibility |
|---|---|---|---|---|
| 1 — Recon | recon |
haiku | low | Inventory the artifact: type, location, criteria list, source files to read. No judgment. |
| 2 — Verify | verifier |
sonnet | medium | Cross-reference each criterion against the source files. Classify as verified, failed, or unverifiable. Neutral — reports evidence only. |
| 3 — Exit Gate | exit-gate |
opus | high | Produce the final verdict. Pass only if all criteria are verified with no unresolved failures. On fail, return specific actionable blockers. |
</three_stage_flow>
<axiom_protocol>
The protocol input is: artifact_type, artifact_path, criteria (explicit or derived from linked spec).
The protocol output is a verdict@1 object: pass or fail, with blockers on failure and a verdict_summary for the orchestrator.
Retry behavior: Up to 3 retries. On each failure, the specific blockers are returned to the producing agent. At retry 3, escalate to the caller — do not loop indefinitely. Track retry_count in the verdict.
</axiom_protocol>
<framework_references>
- Verdict Schema </framework_references>
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.
- 2d ago First seen · 59 lines · 143 tokens per session scan A a74afa941db9
gate is a skill published in the GitHub repository orin-dx/agent-plugins (1 stars, last pushed 5d ago), licensed MIT. It adds 143 tokens to every session and 716 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
campus-assignment-cleaner
Activates when a student or campus developer needs to make a working-but-messy codebase submission-ready before uploading it for grading. Trigger phrasings include "clean up my assignment before submitting", "remove debug prints and commented code", "tidy this up before I upload it to Moodle/Canvas/GitHub Classroom"…
git-workflow-and-versioning
Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump…
advogado-criminal
Advogado criminalista especializado em Maria da Penha, violencia domestica, feminicidio, direito penal brasileiro, medidas protetivas, inquerito policial e acao penal.
agent-evaluation-reporting
Use when summarizing agent evaluations where autonomous, assisted, failed, timed-out, or invalid outcomes must remain distinct and comparable.
agent-orchestration-multi-agent-optimize
Optimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving agent performance, throughput, or reliability.
adhx
Fetch any X/Twitter post as clean LLM-friendly JSON. Converts x.com, twitter.com, or adhx.com links into structured data with full article content, author info, and engagement metrics. No scraping or browser required.