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-technical-review)<a href="https://agentmods.dev/commands/manishiitg/coding-agent-loop/run-technical-review"><img src="https://agentmods.dev/badge/commands/manishiitg/coding-agent-loop/run-technical-review/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-technical-review"><img src="https://agentmods.dev/badge/commands/manishiitg/coding-agent-loop/run-technical-review.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 | $0.00455 |
| Opus 5.5 | $0.00000 | $0.00182 |
| Sonnet 5.5 | $0.00000 | $0.00091 |
| Haiku 4.5 | $0.00000 | $0.00046 |
Grade A, and why
run-technical-review 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 22d 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 /run-technical-review as a BACKGROUND task so this chat stays responsive. If the run_in_background tool is available: call run_in_background with name "Technical review + fix", completion_mode "present_result", the review instruction below, and a message_sequence with one follow-up message (id "fix") carrying the fix instruction below.
Review instruction:
Call get_workflow_command_guidance(kind="engineering-review", focus="{{context}}") and follow the returned instructions verbatim. Pass run_folder as the workflow's currently selected run folder when one is selected; otherwise omit it. If this session is read-only (run mode), return findings in chat only; do not write or edit any workspace file. Otherwise, persist findings, recommendations, and decisions through the typed Pulse tools required by the returned guidance; do not modify implementation files or 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. This is the read-only opening of one retained Review+Fix task. Persist the completed technical_review receipt before ending this turn. The supplied follow-up message owns repair. Small recovered tool failures with correct outputs and negligible overhead do not justify an issue or deeper review.
Fix instruction:
Continue the same bounded Review+Fix task. First confirm this conversation has a completed technical_review receipt; if review failed or is incomplete, report that and do not repair. Then call get_workflow_command_guidance(kind="pulse-fixer") and follow its repair-only instructions, carrying the same focus and run folder. Apply only reviewed, authorized bounded fixes, perform proportional immediate checks, and close applied fixes unless the defect is reproduced. Do not rerun reviewers or create future-run verification tasks. Return the combined review and repair outcome.
Do NOT perform the review + fix 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 same bounded Review+Fix inline: run the review instruction above, and after persisting the review receipt, continue inline with the fix instruction.
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.
- 22d ago First seen · 18 lines · 0 tokens per session scan A a4ee20c3906a
run-technical-review is a command published in the GitHub repository manishiitg/coding-agent-loop (13 stars, last pushed 18d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 455 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
dashboard-session-abort-all
Abort multiple running sessions (asks which). Usage /dashboard:session-abort-all.
dashboard-session-kill
Shut down (kill) a session. DESTRUCTIVE. Usage /dashboard:session-kill.
dashboard-session-info
Show every field of a session by id-prefix. Usage /dashboard:session-info . Runs locally, no LLM.
dashboard-session-rename
Rename a session. Usage /dashboard:session-rename.
dashboard-session-resume
Resume a session (continue mode). Usage /dashboard:session-resume.
dashboard-session-tell
Send a prompt to another session. Usage /dashboard:session-tell.