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/manishiitg/coding-agent-loopWrote 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/manishiitg/coding-agent-loop/run-plan-drift)<a href="https://agentmods.dev/commands/manishiitg/coding-agent-loop/run-plan-drift"><img src="https://agentmods.dev/badge/commands/manishiitg/coding-agent-loop/run-plan-drift/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/manishiitg/coding-agent-loop/run-plan-drift"><img src="https://agentmods.dev/badge/commands/manishiitg/coding-agent-loop/run-plan-drift.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 | $0.00000 | $0.00245 |
| Opus 5.5 | $0.00000 | $0.00098 |
| Sonnet 5.5 | $0.00000 | $0.00049 |
| Haiku 4.5 | $0.00000 | $0.00024 |
Grade A, and why
run-plan-drift 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 23d 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 /run-plan-drift review as a BACKGROUND task so this chat stays responsive. If the run_in_background tool is available: call run_in_background with name "Plan Drift review", completion_mode "present_result", and this instruction:
Call get_workflow_command_guidance(kind="review-artifact-drift", focus="{{context}}") and follow the returned instructions verbatim. If this session is read-only (run mode), return findings in chat only; do not write or edit any workspace file. Otherwise, follow the Plan Drift authority in the returned guidance: Part 1 may apply bounded safe compatibility and prompt repairs; Part 2 remains read-only. Persist typed review and repair outcomes; do not write a separate review file. Treat focus as the request context, including recent user constraints. Apply conditional checks only when relevant to the selected investigation.
Do NOT perform the review yourself this turn — you'll get a presentation-only completion notification, then present the selected repair objective, changes made, immediate checks and their limits, lifecycle outcomes, and remaining actionable issues. Do not call tools, reload state, or independently revalidate after that notification. If run_in_background is not available, perform the review inline using these same instructions.
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.
- 23d ago First seen · 11 lines · 0 tokens per session scan A ab31c8150c01
run-plan-drift is a command published in the GitHub repository manishiitg/coding-agent-loop (13 stars, last pushed 19d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 245 tokens. 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 2026-09-24.
Other commands, from other repositories
go
You MUST start your FIRST response with this exact agent activation line.
dashboard-session-tell
Send a prompt to another session. Usage /dashboard:session-tell.
dashboard-session-fork
Fork a session into a new one. Usage /dashboard:session-fork.
dashboard-session-hide
Hide a session from the dashboard list. Usage /dashboard:session-hide.
orchestrate
You MUST start your FIRST response with this exact agent activation line.
protocol-orchestration
You MUST start your FIRST response with this exact agent activation line.