Borrowing it
Nothing to install: this file belongs to vladm3105/aidoc-flow-framework. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vladm3105/aidoc-flow-framework/dev/.agents/skills/approval-gate/SKILL.mdgit clone --depth 1 https://github.com/vladm3105/aidoc-flow-frameworkWrote 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/vladm3105/aidoc-flow-framework/approval-gate)<a href="https://agentmods.dev/skills/vladm3105/aidoc-flow-framework/approval-gate"><img src="https://agentmods.dev/badge/skills/vladm3105/aidoc-flow-framework/approval-gate/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/vladm3105/aidoc-flow-framework/approval-gate"><img src="https://agentmods.dev/badge/skills/vladm3105/aidoc-flow-framework/approval-gate.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00051 | $0.01140 |
| Opus 5.5 | $0.00020 | $0.00456 |
| Sonnet 5.5 | $0.00010 | $0.00228 |
| Haiku 4.5 | $0.00005 | $0.00114 |
Grade A, and why
approval-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 10d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Approval gate
Before acting on the outside world, classify the action and route it. Never self-approve: an agent drafts and proposes; a human authorizes anything external or irreversible.
Standing authorization is not self-approval. Where the human or the active repository has authorized a class of action in advance and in writing, acting within it executes that decision. Merge-on-green exists only where the active repository explicitly grants it; the global rules supply safety carve-outs but not merge authority. Red or incomplete CI always means do not merge.
Tiers
| Tier | Examples | Do |
|---|---|---|
| 🟢 Act directly | commits on your own branch · drafts · internal messages · research and analysis · anything reversible inside your own workspace using approved tech stack tools | proceed |
| 🟡 Needs human OK | send external email · public posts · publish a site or docs · spend, pricing or contract changes · Missing Tools escalation (in autonomous sessions, always file a GitHub issue detailing the missing tool requirement; interactively, request operator instructions when a needed tool is missing from /home/ya/devd/technology_stack) · conflict disposition (file GitHub issues for real deployment/selection work) · anything a stranger will see |
prepare the artifact below, then stop and surface it |
| 🔴 Never autonomous | financial commitments · legal execution · hiring · force-push · destructive data operations · writes to a repo you are not working in · offering, proposing, or using insecure options (plaintext secrets, disabled sandboxing, bypassed verification --no-verify, relaxed permissions) |
flag to the human; do not prepare it for auto-execution; reject insecure options outright |
When unsure which tier, treat it as the higher one. The cost of over-routing is a few minutes; the cost of under-routing is unrecoverable.
Two distinctions that get missed:
- Reversibility is not the only test. An action can be technically reversible and still 🟡 because someone already saw it — a deleted post was still read, a sent email was still received.
- Verbal authorization in chat does not by itself make a durable record. Where an audit trail matters, the artifact is the record; a transcript is not one. (Some projects make this a hard rule — see the workspace section.)
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.
- 10d ago Changed d4119c811880
- 1mo ago First seen · 93 lines · 51 tokens per session scan A 8797fdd65ff4
approval-gate is a skill published in the GitHub repository vladm3105/aidoc-flow-framework (17 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 1,140 once invoked, about $0.0002 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 2026-09-28.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
remove
Remove a deployed framework or addon from the current workspace.