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/luiseiman/dotforgeWrote 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/luiseiman/dotforge/forge-compact-task)<a href="https://agentmods.dev/commands/luiseiman/dotforge/forge-compact-task"><img src="https://agentmods.dev/badge/commands/luiseiman/dotforge/forge-compact-task/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/luiseiman/dotforge/forge-compact-task"><img src="https://agentmods.dev/badge/commands/luiseiman/dotforge/forge-compact-task.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00046 | $0.00276 |
| Opus 5.5 | $0.00018 | $0.00110 |
| Sonnet 5.5 | $0.00009 | $0.00055 |
| Haiku 4.5 | $0.00005 | $0.00028 |
Grade A, and why
forge-compact-task 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 1mo 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.
What it actually says
Run the /compact slash command with this exact hint:
preserve: active task description, files modified this session, decisions made (architecture, security, naming), pending TODOs, behaviors disabled in this session, last commit hash and message. drop: tool output verbose (find, grep, ls dumps), intermediate searches that didn't lead anywhere, redundant explanations.
Why a custom hint matters (per evidence from X practitioners): default auto-compact may drop info you know is critical. Passing explicit preservation instructions improves summary fidelity.
When to use this command:
- ~80% of context window (operational threshold from research, not academic 50% nor default 96.7%)
- Between distinct tasks within the same project
- Before a long break (>4h) so the next session resumes with quality summary
- Before delegating to a subagent so the parent context is light
When NOT to use:
- <70% context: summary would lose recent thread
- New project: use
/clearinstead (full reset) - Switching between unrelated tasks: subagent or
/clear
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.
- 1mo ago First seen · 24 lines · 46 tokens per session scan A 9d23311ba582
forge-compact-task is a command published in the GitHub repository luiseiman/dotforge (8 stars, last pushed 9d ago), licensed MIT. It adds 46 tokens to every session and 276 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.
Other commands, from other repositories
retex
Retex - Capture lesson learned dans memory après fix, rollback, erreur.
context-stats
Display context window usage and token statistics.
handoff
Write a session handoff document for continuity.
argos
A command for checking whether an implementation matches its design deliverables. Its Korean description compares the work to the design as part of a completion inspection.
ccc-context-budget
Show how full the context window is, which components use the most of it, and when to save the session and compact. Use when the session feels slow, long or near its context limit.
lessons
Lists the feedback memories captured for the current project (and globally) — the "lessons" learned from user corrections.