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 commands/jayvee/aigon/helpgit clone --depth 1 https://github.com/jayvee/aigonWrote 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/commands/jayvee/aigon/help)<a href="https://agentmods.dev/commands/jayvee/aigon/help"><img src="https://agentmods.dev/badge/commands/jayvee/aigon/help.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 | $0.00004 | $0.01457 |
| Opus 5 | $0.00002 | $0.00728 |
| Sonnet 5 | $0.00001 | $0.00291 |
| Haiku 4.5 | $0.00000 | $0.00146 |
Grade A, and why
help 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 yesterday.
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.
This is a copy
98% identical to ah — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Aigon Commands
Feature Commands (unified for Drive and Fleet modes)
| Command | Description |
|---|---|
/aigon:feature-create <name> |
Create a new feature spec |
/aigon:feature-now <name> |
Fast-track: inbox → prioritise → setup → implement, or create new + implement |
/aigon:feature-prioritise <name> |
Assign ID and prioritise to backlog |
/aigon:feature-start <ID> [agents...] |
Setup for Drive (branch) or Fleet (worktrees) |
/aigon:feature-do <ID> [--iterate] |
Do feature work; --iterate enables the Autopilot retry loop |
/aigon:feature-spec <ID> [--json] |
Resolve the canonical visible spec path for a feature |
/aigon:feature-list [--active] [--all] [--json] |
Query feature records without going through the board UI |
/aigon:feature-eval <ID> |
Create evaluation (code review or comparison) |
/aigon:feature-code-review <ID> |
Code review with fixes by a different agent |
/aigon:feature-code-revise [ID] |
Implementer-side: read the review and decide accept/challenge/modify (infers ID from worktree branch) |
/aigon:feature-spec-review <ID> |
Review the feature spec itself before implementation |
/aigon:feature-spec-revise <ID> |
Author-side: process pending spec reviews in one pass |
/aigon:feature-push [ID] [agent] |
Push feature branch to origin for PR review |
/aigon:feature-close <ID> [agent] |
Merge and complete feature |
/aigon:feature-cleanup <ID> |
Clean up Fleet worktrees and branches |
/aigon:feature-autonomous-start <ID> <agents...> |
Start autonomous feature flow with explicit stop-after control |
/aigon:feature-open [ID] [agent] |
Open feature worktree in terminal and start agent |
Research (unified for Drive and Fleet modes)
| Command | Description |
|---|---|
/aigon:research-create <name> |
Create a new research topic |
/aigon:research-prioritise <name> |
Prioritise a research topic |
/aigon:research-start <ID> [agents...] |
Setup for Drive or Fleet execution |
/aigon:research-open <ID> |
Re-open or attach Fleet research sessions |
/aigon:research-do <ID> |
Conduct research (write findings) |
/aigon:research-spec-review <ID> |
Review the research spec itself before execution |
/aigon:research-spec-revise <ID> |
Author-side: process pending research spec reviews in one pass |
/aigon:research-eval <ID> |
Evaluate or synthesize parallel findings |
/aigon:research-close <ID> |
Complete a research topic |
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.
- yesterday First seen · 102 lines · 4 tokens per session scan A 49a3d3759fab
help is a command published in the GitHub repository jayvee/aigon (25 stars, last pushed 4d ago), licensed Apache-2.0. It adds 4 tokens to every session and 1,457 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to ah, differing in 2 lines, and is treated as a copy.
Other commands, from other repositories
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
journey-audit
Outside-in product audit as a deep session — 7 read-only roles check what the site promises against what the code does, what a user experiences, what arrives by mail, and what the data says is used. Writes a dossier; needs a per-repo journey-manifest.
cost-tracker
Track session costs, understand token spend, and get optimization tips.
workpm
PM 모드로 오케스트레이터 시작. 팀을 구성하고 5단계 워크플로우로 작업을 완수합니다.
mach12:gh-pr-read
Read a GitHub pull request's title, body, and all top-level PR conversation comments; optionally locate an HTML-marker comment.
argos
설계 산출물 대비 구현 검증 — 준공검사 감리 (아르고스).