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/feature-startgit 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/feature-start)<a href="https://agentmods.dev/commands/jayvee/aigon/feature-start"><img src="https://agentmods.dev/badge/commands/jayvee/aigon/feature-start.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 | $0.00014 | $0.00591 |
| Opus 5 | $0.00007 | $0.00296 |
| Sonnet 5 | $0.00003 | $0.00118 |
| Haiku 4.5 | $0.00001 | $0.00059 |
Grade A, and why
feature-start 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 3d 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.
This is a copy
100% identical to afs — 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
aigon-feature-start
Prepare your workspace to implement a feature in Drive or Fleet mode.
CRITICAL: Use the CLI command below. Do NOT manually move spec files, lifecycle-view links, create branches, or create worktrees — the CLI records the workflow transition and prepares branch/worktree state.
Argument Resolution
If no ID is provided or doesn't match a backlog entry, list ./docs/specs/features/02-backlog/feature-*.md, filter to matches, and ask the user to choose.
Step 1: Run the CLI
Pass EXACTLY the args the user provided. Do NOT add agents that weren't specified.
# Drive mode (branch in current repo) — ID only
aigon feature-start {{args}}
# Drive worktree mode (parallel development) — ID + 1 agent
aigon feature-start {{args}} <agent>
# Fleet mode (competition) — ID + 2+ agents
aigon feature-start {{args}} <agent1> <agent2> [agent3...]
Mode is determined by arg count (0 / 1 / 2+ agents). The CLI transitions the feature from backlog to in-progress, refreshes the generated lifecycle view (stable layout), creates branch or worktree(s), and creates implementation log(s).
If the CLI reports errors while recording or publishing the workflow transition, resolve them before proceeding.
Step 2: Confirm setup and next steps
feature-start creates the workspace AND opens agent terminals automatically — there is no separate "open" step.
- Drive mode (branch): you end up on the feature branch in your current terminal. Start implementation manually with
/aigon:feature-do <ID>. Close with/aigon:feature-close <ID>when done. - Drive worktree: agent terminal is already running. Wait for submit, then
/aigon:feature-close <ID>from the main repo. - Fleet: all agent terminals are running and implementing. Wait for all to submit, then
/aigon:feature-eval <ID>. - Re-open a crashed session:
/aigon:feature-open <ID>(or/aigon:feature-open <ID> <agent>for a specific Fleet agent).
Worktrees are created in ../<repo>-worktrees/ to keep them grouped with the project.
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.
- 3d ago First seen · 50 lines · 14 tokens per session scan A 2d9fb842da5e
feature-start is a command published in the GitHub repository jayvee/aigon (25 stars, last pushed 5d ago), licensed Apache-2.0. It adds 14 tokens to every session and 591 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to afs, differing in 2 lines, and is treated as a copy.
Other commands, from other repositories
create-issue
Create a GitHub issue with proper template discovery and population.
mach12:issue-implement
Implement a specific stage of an issue's implementation plan.
mach12:plan-comment-contract
Apply the canonical contract for a durable implementation-plan comment.
update-config
Update Dark Flow project settings: language and/or main branch.
mach12:issue-create
Create a structured GitHub issue from current context or description.
status
Cross-project status check — pull current state from /CLAUDE.md + vault + git.