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 AdityaVasireddy/agent-skills --skill five-gate-methodgit clone --depth 1 https://github.com/AdityaVasireddy/agent-skillsWrote 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/adityavasireddy/agent-skills/five-gate-method)<a href="https://agentmods.dev/skills/adityavasireddy/agent-skills/five-gate-method"><img src="https://agentmods.dev/badge/skills/adityavasireddy/agent-skills/five-gate-method.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 5.1 | $0.00220 | $0.03110 |
| Opus 5 | $0.00110 | $0.01555 |
| Sonnet 5 | $0.00044 | $0.00622 |
| Haiku 4.5 | $0.00022 | $0.00311 |
Grade A, and why
five-gate-method 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 8d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Five-Gate Method
An operating discipline for hard tasks, written down so any capable model can run it. It doesn't transfer intelligence; it transfers how the work is managed: how to scope, gather evidence, attack your own answers, verify, and report.
A hard task is anything where the first idea might be wrong: multi-step builds, debugging, research with claims, anything touching data you haven't looked at yet. For a one-file edit or a simple lookup, skip the gates and just do the work.
Why the gates exist
Each gate eliminates a different class of failure:
- Gate 1 prevents solving the wrong problem.
- Gate 2 prevents reasoning from false premises.
- Gate 3 prevents fixation on the first explanation.
- Gate 4 prevents confusing execution with success.
- Gate 5 prevents overstating certainty.
The loop: five gates, in order
Every hard task passes through five gates. A gate must pass before the next one opens. When a task stalls or a result surprises you, name which gate you're at and re-run it.
Rollback goes as deep as the damage: a later gate can invalidate an earlier one. When verification contradicts the plan, return to the earliest gate whose assumptions changed — not merely the previous gate. A failed Gate 4 sometimes means Gate 2 gathered thin evidence, and sometimes means Gate 1 defined the wrong "done."
Entering mid-task. You don't have to start at Gate 1. Most of the time this discipline is needed, work is already underway and something has gone sideways. Find the earliest gate whose pass condition you cannot currently produce evidence for, and resume there. If you can't name what done looks like, you're at Gate 1 regardless of how much has been built.
Rollback is bounded. If the same gate fails twice on the same task, stop cycling — that repetition is itself a finding. Either the task as scoped is not achievable with the evidence available, or a load-bearing unknown from Gate 1 was never named. Go to Gate 5 and report the incomplete state honestly: what is verified, what is blocked, and what you would need to unblock it. Reporting an unfinished task accurately is a pass, not a failure; grinding the loop to avoid saying so is a Gate 5 violation.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 146 lines · 220 tokens per session scan A 11caf15d8971
five-gate-method is a skill published in the GitHub repository AdityaVasireddy/agent-skills (2 stars, last pushed today), licensed MIT. It adds 220 tokens to every session and 3,110 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
prisma-client-api
Prisma Client API reference covering model queries, filters, operators, and client methods. Use when writing database queries, using CRUD operations, filtering data, or configuring Prisma Client. Triggers on "prisma query", "findMany", "create", "update", "delete", "$transaction".
sns
AWS SNS notification service for pub/sub messaging. Use when creating topics, managing subscriptions, configuring message filtering, sending notifications, or setting up mobile push.
cognito
AWS Cognito user authentication and authorization service. Use when setting up user pools, configuring identity pools, implementing OAuth flows, managing user attributes, or integrating with social identity providers.
eventbridge
AWS EventBridge serverless event bus for event-driven architectures. Use when creating rules, configuring event patterns, setting up scheduled events, integrating with SaaS, or building cross-account event routing.
iam
AWS Identity and Access Management for users, roles, policies, and permissions. Use when creating IAM policies, configuring cross-account access, setting up service roles, troubleshooting permission errors, or managing access control.
agent-ready-cloudflare
Audit and improve website readiness for AI agents using the Cloudflare "Is It Agent Ready?" scanner (isitagentready.com). Covers scanning via API, interpreting results, generating implementation prompts, and fixing every check. Use when the user mentions "agent ready", "isitagentready", "AI agent scan", "agent…