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.
git clone --depth 1 https://github.com/bearded-illirian/trailmarkWrote 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/bearded-illirian/trailmark/go-fast)<a href="https://agentmods.dev/commands/bearded-illirian/trailmark/go-fast"><img src="https://agentmods.dev/badge/commands/bearded-illirian/trailmark/go-fast.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 | $0.00079 | $0.01390 |
| Opus 5 | $0.00039 | $0.00695 |
| Sonnet 5 | $0.00016 | $0.00278 |
| Haiku 4.5 | $0.00008 | $0.00139 |
Grade A, and why
go-fast 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 7d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/go-fast
Thin entry point into a self-organizing skill chain for a fast-track task.
Creates a task and passes control to idea-first. The chain then runs
autonomously via Skill() calls:
go-fast → idea-first → habit-first / arch-first / audit-first → per-block cycle → ship-first
Usage:
/go-fast {task description}— inline description/go-fast— asks for description
Input
A task description (inline after /go-fast or requested via prompt); optional project id from a prior /go-start invocation.
Output
A task folder {tasks_root}/log/{date}-{slug}/ containing task.md; a new row in routing.db artifacts table with status='open'; session context ({slug}, {log_dir}, {project_id}) populated for downstream skills.
Hands off to
idea-first — determines task type (product / feature / fix) and routes to the correct branch (habit-first / arch-first / audit-first).
Step 1 — Determine project
Early return — if {project_id}, {project_path} and {project_name} are already set in session context (e.g. after /go-start) — use them without re-asking. Output confirmation with override option:
Using project from go-start: {project_name}
Override? (Enter / no — continue with this, or number from list)
1. {project 1}
2. {project 2}
...
| Response | Action |
|---|---|
| Enter, "no", empty | Use the set {project_id} — go to Step 2 |
| Number from list | Set new {project_id} + {project_path} + {project_name} — go to Step 2 |
Standard flow — if {project_id} is NOT set (go-fast called without go-start):
Read the projects config and show only status: active projects:
Which project is this task for?
1. {project 1}
2. {project 2}
...
Enter number:
Wait for answer. Save chosen project id and path as session context: {project_id}, {project_path}, {project_name}.
Step 2 — Receive task
If task description was provided inline after /go-fast — use it directly.
If not provided — ask What are we doing? and wait.
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.
- 7d ago First seen · 158 lines · 79 tokens per session scan A 66eeeac2e0a2
go-fast is a command published in the GitHub repository bearded-illirian/trailmark (19 stars, last pushed 5d ago), licensed MIT. It adds 79 tokens to every session and 1,390 once invoked, about $0.0004 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
afsr
Review feature spec - improve the spec itself before implementation (shortcut for feature-spec-review).
next
Suggest the most likely next workflow action based on current context.
research-do
Do research - agent writes findings.
research-spec-review
Review research spec - improve the research brief before execution.
afe
Evaluate feature - code review or comparison (shortcut for feature-eval).
research-autopilot
Research autopilot [agents...] - Fleet setup + spawn + monitor + evaluate.