watch-runs

watch-runs is a command for coding agents from zhyx12/projtool. It costs 24 tokens per session (742 once invoked), scanned A, original, MIT.

A monitoring command that follows every active research run until it reaches a finished state. It checks progress in stages instead of continuously polling.

In plain words
What is it for?
Use it to monitor runs, finalize those that have exited, report their progress, flag suspected stalls, and summarize the final statuses.
Why use it?
It removes the need to repeatedly check long-running jobs and helps distinguish a real stall from a quiet parent process with newer progress elsewhere.

Command

Install

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.

agentmods
npx agentmods add commands/zhyx12/projtool/watch-runs
Clone the repo
git clone --depth 1 https://github.com/zhyx12/projtool

Wrote 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.

agentmods badge for watch-runs

README.md
[![agentmods](https://agentmods.dev/badge/commands/zhyx12/projtool/watch-runs.svg)](https://agentmods.dev/commands/zhyx12/projtool/watch-runs)
Your own site
<a href="https://agentmods.dev/commands/zhyx12/projtool/watch-runs"><img src="https://agentmods.dev/badge/commands/zhyx12/projtool/watch-runs.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 742 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00024 $0.00742
Opus 5 $0.00012 $0.00371
Sonnet 5 $0.00005 $0.00148
Haiku 4.5 $0.00002 $0.00074

Measured 3d ago against content hash 499262a7a875, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

watch-runs 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.

src/projtool/assets/project_templates/claude/commands/watch-runs.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/watch-runs — caretaker loop for active runs

Watch every non-terminal run of this project until all reach a terminal state, without the user having to ask "怎么样了".

Protocol

  1. Inventory. mcp__projtool__list_run_statuses(experiment_id=...) for each experiment with active runs (start from mcp__projtool__list_runs if unsure). Note each run's phase, progress_age_s, and stalled_suspect.
  2. Close what already exited. Newly exited runs (exit sentinel present): mcp__projtool__finalize_runs(experiment_id=..., then=<policy>) — one call per experiment, one journal commit per batch.
  3. Report briefly. One line per active run: run_id tail, phase, progress age. Flag stalled_suspect=true runs — check their progress_sources before declaring a stall (pool launchers with declared progress_paths often show a fresh source behind a quiet parent log).
  4. Schedule the next check with ScheduleWakeup (or your harness's scheduler): first check ~5 min after launch, then 15 → 30 → 45 min as runs prove stable. NEVER busy-wait or run while true; do ssh loops.
  5. Repeat 1–4 on each wake until no non-terminal runs remain.
  6. Finish. Summarize outcomes (per-status counts, headline metrics from compare_runs), confirm the instance policy took effect (list_instances — nothing billing idle), and suggest /retrospective to distill findings.

Completion by artifact, not just process exit

Some runs signal "done" by dropping a filemetrics.json, a .ok/.done sentinel — rather than by the process exiting, so their exit sentinel may never land on the schedule you expect. For those runs, treat the expected artifact's presence as the completion signal.

On EACH scheduled wake (step 4), probe for it once — a single mcp__projtool__read_remote_file(...) or mcp__projtool__remote_exec(command="test -f <path> && echo DROPPED") call, using the run's declared outputs / progress_paths when present. One probe per wake, then let the schedule pace you.

Read the full file on GitHub · 62 lines

Changes

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.

  1. 3d ago First seen · 62 lines · 24 tokens per session scan A 499262a7a875

Subscribe to this mod's changes

watch-runs is a command published in the GitHub repository zhyx12/projtool (1 stars, last pushed 20d ago), licensed MIT. It adds 24 tokens to every session and 742 once invoked, about $0.0001 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 2026-08-31.