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/afclgit 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/afcl)<a href="https://agentmods.dev/commands/jayvee/aigon/afcl"><img src="https://agentmods.dev/badge/commands/jayvee/aigon/afcl.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 | $0.00030 | $0.02167 |
| Opus 5 | $0.00015 | $0.01084 |
| Sonnet 5 | $0.00006 | $0.00433 |
| Haiku 4.5 | $0.00003 | $0.00217 |
Grade A, and why
afcl 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- feature-close — 95% identical, 2 lines differ
- aigon-feature-close — 91% identical, 35 lines differ
How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
aigon-feature-close
Complete a feature by merging the implementation and cleaning up.
Argument Resolution
If no ID is provided, or the ID doesn't match an existing feature:
- Run
aigon feature-list --active - If a partial ID or name was given, filter to matches
- Present the matching features and ask the user to choose one
Usage
Drive mode (branch or worktree)
If you used feature-start {{args}} or feature-start {{args}} <agent>:
aigon feature-close {{args}}
The command auto-detects whether the feature uses a branch or a Drive worktree.
Fleet mode
If you used feature-start {{args}} cc ag cx cu:
aigon feature-close {{args}} <winning-agent>
Example: aigon feature-close {{args}} cc to merge Claude's implementation
Fleet mode with adoption
Merge the winner and print diffs from losing agents for selective adoption:
aigon feature-close {{args}} <winning-agent> --adopt <agents...|all>
Examples:
aigon feature-close {{args}} cc --adopt ag cu— adopt from specific agentsaigon feature-close {{args}} cc --adopt all— adopt from all losing agents
What happens
Drive Mode
- If on the feature branch with uncommitted changes, auto-commits them (
feat: implementation for feature <ID>) - Pushes the feature branch to origin (to save work remotely)
- Switches to main/master branch
- Merges the feature branch with
--no-ff - Records done lifecycle and refreshes the generated view
- Moves implementation log to
logs/selected/ - Deletes the local feature branch
- Commits the spec and log moves
Fleet Mode (without --adopt)
- Pushes the winning agent's branch to origin
- Switches to main/master branch
- Merges the winning agent's branch with
--no-ff - Records done lifecycle and refreshes the generated view
- Organizes logs:
- Winning agent's log →
logs/selected/ - Other agents' logs →
logs/alternatives/
- Winning agent's log →
- Removes the winning agent's worktree
- Deletes the winning agent's local branch
- Commits the changes
- Shows cleanup options for remaining worktrees/branches
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 · 208 lines · 30 tokens per session scan A 643a9620aabd
afcl is a command published in the GitHub repository jayvee/aigon (25 stars, last pushed 4d ago), licensed Apache-2.0. It adds 30 tokens to every session and 2,167 once invoked, about $0.0002 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 2026-09-03.
Other commands, from other repositories
commit-changes
Review all uncommitted changes and create a well-structured commit using conventional commit format.
commit
Create a well-crafted commit after running pro-workflow quality checks.
close
End session with verification, commits, and documentation.
commit-all
Stage and commit all current changes with a single message. Auto Git Push will pick up and push to origin within 30s.
preflight
Pre-commit checks for RondoFlow — format, lint/typecheck, and tests across the workspace.
sprint-close
Close the current sprint — build, test, update sprint docs, commit (optional push).