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/baixinghao/intent-gate/using-intent-gatenpx skills add baixinghao/intent-gate --skill using-intent-gategit clone --depth 1 https://github.com/baixinghao/intent-gateWhat 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 | $0.00067 | $0.01363 |
| Opus 5 | $0.00034 | $0.00681 |
| Sonnet 5 | $0.00013 | $0.00273 |
| Haiku 4.5 | $0.00007 | $0.00136 |
Grade A, and why
using-intent-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.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A "reasonable technical assumption" is NOT intent alignment. Silent assumptions on core flows are the #1 source of rework this gate exists to prevent.
The Rule
Before acting on anything uncertain, irreversible, or business-critical, check the gate:
- Requirement analysis tasks → FIRST read the MCP prompt
doc_analysis_playbookin full. It is the law: confidence assessment (Step 0), intent alignment loop (Step 0.5), artifact gates (Step 4). Do not analyze from memory. - Confidence red/yellow on a decision → use the intent-gate tools instead of
assuming. Red light on a core flow means the work is
blockeduntil a human answers. - Everything is non-blocking — dispatch the question, persist it, continue other work or end the turn. Answers are reconciled on session resume.
Optional Add-ons（可选项，不用不启动）
- 红蓝对抗评审（skill
red-blue-review） — after a complex requirement's summary.md is delivered, the human may opt into an adversarial review: a blue army in an INDEPENDENT session audits the artifacts against R1-R9 and writes findings. PASS is one of only two legitimate paths tostatus: approved(the other is a direct human decision). Never run it uninvited; never run it in the red army's session. - 钉钉群共识通道（姊妹篇 intent-gate-service MCP 服务） — intent questions whose rightful
answerer sits in a DingTalk group (📋 business / 🔧 technical) can be dispatched
there via intent-gate-service's
group_dispatchtool; blocking human-decision gates (ask_human) also live there. If the intent-gate-service MCP is not mounted, this project simply uses the dialog fallback — do not treat its absence as an error.
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 · 100 lines · 67 tokens per session scan A 6126f4f2bf60
using-intent-gate is a skill published in the GitHub repository baixinghao/intent-gate (2 stars, last pushed 18d ago), licensed MIT. It adds 67 tokens to every session and 1,363 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 2026-08-31.
Other skills, from other repositories
build-teaql-app
Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…
swe-af
Autonomous engineering team runtime — one API call spins up coordinated AI agents to scope, build, and ship software.
delegate-issue
Delegate well-scoped coding issues to a SWE-AF node as a cheap sub-harness via implementissue, then collect and merge the returned branches. Use when the user asks to offload, delegate, or fan out scoped tasks to SWE-AF / swe-planner / swe-fast, or when several independent, fully-specified changes could run in…
add-wshcmd
Guide for adding new wsh commands to Wave Terminal. Use when implementing new CLI commands, adding command-line functionality, or extending the wsh command interface.
add-config
Guide for adding new configuration settings to Wave Terminal. Use when adding a new setting to the configuration system, implementing a new config key, or adding user-customizable settings.
create-view
Guide for implementing a new view type in Wave Terminal. Use when creating a new view component, implementing the ViewModel interface, registering a new view type in BlockRegistry, or adding a new content type to display within blocks.