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/fatihguner/foreman/implementation-commandsgit clone --depth 1 https://github.com/fatihguner/foremanWhat 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 | $0.00045 | $0.03550 |
| Opus 5 | $0.00023 | $0.01775 |
| Sonnet 5 | $0.00009 | $0.00710 |
| Haiku 4.5 | $0.00005 | $0.00355 |
Grade A, and why
implementation-commands 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.
How it starts
The opening of the file, as written. The whole thing — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementation Commands
/track
Description
Displays all active implementation items -- every recommendation from playbooks, skills, and diagnostics that has entered the tracking system and has not yet reached a terminal state. The default view shows all non-terminal items sorted by deadline proximity. Status filters narrow the view to a specific state. The overdue filter is a computed view: it surfaces items past their deadline that have not been completed, regardless of their current status.
This is the command for situational awareness. Run it at the start of a session to see what is in flight, what is stuck, and what is due.
Syntax
/track [status-filter]
Parameters
| Parameter | Required | Type | Default | Description |
|---|---|---|---|---|
status-filter |
No | string | all active | Filter by status: not-started, in-progress, blocked, completed, abandoned, deferred, overdue, stalled |
Examples
/track
--> Implementation Tracker: 12 active items
3 not-started | 5 in-progress | 2 blocked | 1 deferred | 1 overdue
[Table: ID | Description | Status | Progress | Deadline | Last Check-in]
impl-001 Redesign BMC for B2B pivot in-progress 40% Apr 15 Apr 08
impl-002 Validate pricing with 10 prospects in-progress 70% Apr 10 Apr 08
impl-003 Draft investor narrative for pivot not-started 0% Apr 20 --
...
/track blocked
--> Blocked Items: 2
[Table: ID | Description | Blocker Category | Blocker | Days Blocked]
impl-005 Hire freelance designer resource Budget not approved 12
impl-008 Integrate partner API dependency Waiting on partner SDK 7
/track in-progress
--> In-Progress Items: 5
[Table: ID | Description | Progress | Deadline | Trend]
impl-001 Redesign BMC for B2B pivot 40% Apr 15 +20% this week
impl-002 Validate pricing with 10 prospects 70% Apr 10 +30% this week
...
/track overdue
--> Overdue Items: 1
[Table: ID | Description | Status | Progress | Deadline | Days Overdue]
impl-004 Complete competitive analysis in-progress 25% Apr 01 7 days overdue
/track stalled
--> Stalled Items (no progress for 14+ days): 2
[Table: ID | Description | Progress | Last Change | Days Stalled]
impl-005 Hire freelance designer 10% Mar 25 14 days
impl-009 Document onboarding process 0% Mar 22 17 days
Recommendation: Run /blockers to analyze what is preventing movement.
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 · 352 lines · 45 tokens per session scan A bb22853d47c3
implementation-commands is a command published in the GitHub repository fatihguner/foreman (47 stars, last pushed 5mo ago), licensed MIT. It adds 45 tokens to every session and 3,550 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 2026-08-30.
Other commands, from other repositories
compress
压缩对话上下文，归档低价值 turns，保留近期 + 决策内容.
inbox-process
处理 meta/queue/to-process/，逐条判断是否写入 wiki、归档、延期或拒收.
download
description: Download Modellix task results to a local directory before the resource URLs expire. argument-hint: [optional task id] [optional output directory].
tasks
Inspect Modellix task status and recover tasks after a timeout or unknown submission.
autobot-result
Print the most recent result.md for an autobot session, so the user can see how a bot is doing without attaching to its tmux session.
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.