watch-run

watch-run is a skill for Claude Code from shaahink/conductor. It costs 51 tokens per session (974 once invoked), scanned A, original, MIT.

Instructions for watching a live Conductor run overnight, where a Conductor run is an automated coding workflow recorded in a log. It defines which events should trigger a notification or limited intervention.

In plain words
What is it for?
Use it to arm one persistent log monitor, detect failures or runs needing human attention, and apply the specified control actions without editing the repository.
Why use it?
It reduces the need to watch the log continuously while still reporting quota problems, repeated loops, crashes, stalls and other important events.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

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 skills/shaahink/conductor/watch-run
Any agent
npx skills add shaahink/conductor --skill watch-run
Clone the repo
git clone --depth 1 https://github.com/shaahink/conductor

Made for: Claude Code.

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-run

README.md
[![agentmods](https://agentmods.dev/badge/skills/shaahink/conductor/watch-run.svg)](https://agentmods.dev/skills/shaahink/conductor/watch-run)
Your own site
<a href="https://agentmods.dev/skills/shaahink/conductor/watch-run"><img src="https://agentmods.dev/badge/skills/shaahink/conductor/watch-run.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 974 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 5.1 $0.00051 $0.00974
Opus 5 $0.00026 $0.00487
Sonnet 5 $0.00010 $0.00195
Haiku 4.5 $0.00005 $0.00097

Measured 6d ago against content hash 65538dce559a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

watch-run 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 6d 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.

.claude/skills/watch-run/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the night watch for a live conductor run. Your job is cheap vigilance: sit silent between events, wake only on the filtered signals below, intervene with control verbs only when a rule fires, and keep every reaction to 1–3 lines. You are NOT the delivering agent — never edit the repo, never commit, never start/stop sessions by hand beyond the verbs listed here.

Arm the watch (one Monitor, persistent)

The engine appends every meaningful line to <repo>/.conductor/conductor.log regardless of how the run was started (owner terminal with Face, or headless). Default repo: C:/code/conductor-baton, default plan: plans/conductor-ux.plan.json — confirm with the user only if the prompt says otherwise.

Arm exactly one persistent Monitor:

tail -F "C:/code/conductor-baton/.conductor/conductor.log" | grep -E --line-buffered "session #[0-9]+ (start|exited|rolled over)|verifier (score|passed|failed|produced)|NEEDS HUMAN|needs-attention|parked|stall|backing off|usage limit|abort|cancelled|state saved|WARNING|circuit|--max-sessions|crash|discarded"

Then tell the user the watch is armed and go quiet. Do not poll. Do not schedule wakeups.

Intervention rules (check top to bottom on each event batch)

The plan's own rails already bound a runaway: per-stage attempts cap at 2× the stage's session budget then park; maxResumesPerSession 3; sessionTimeoutMinutes 90; maxSessions 40 then stop; repeated agent-backend refusals park NeedsHuman after MaxBackoffs. Your job is the early cut and the phone call, not re-implementing those rails.

  1. Quota guard — any usage limit / backing off line: first one, note it silently. Second within the same run: conductor pause -p <plan> and send a PushNotification ("run paused — agent backend refusing, check quota"). This is the drain-a-Claude-plan-in-a-loop scenario.
  2. Churn loop — the same stage shows Fix/Verify attempt lines reaching attempt N/M with N ≥ 4, or 3 consecutive sessions exit in under ~2 minutes each: conductor pause -p <plan>, PushNotification ("run paused — is churning attempts without progress").
  3. ParkNEEDS HUMAN / parked / AwaitingOwner: the engine already stopped spawning. PushNotification with the reason line. No verb needed.
  4. Run endedstate saved / --max-sessions / abort: PushNotification with a one-line summary (conductor status -p <plan> for checkpoint counts — it is offline and cheap by default).
  5. Healthy traffic (session start/exit, gates PASS, verifier passed, workflow steps): no reply at all, or at most one line if several checkpoints just confirmed. Silence is the correct output for a healthy run.

Read the full file on GitHub · 63 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. 6d ago First seen · 63 lines · 51 tokens per session scan A 65538dce559a

Subscribe to this mod's changes

watch-run is a skill published in the GitHub repository shaahink/conductor (5 stars, last pushed 9d ago), licensed MIT. It adds 51 tokens to every session and 974 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

cratis-react-page

Step-by-step guidance for building a React page in a Cratis Arc application — DataPage lists, CommandDialog toolbar actions, confirmation and busy-indicator dialogs, row selection, details components, observable queries, and MVVM. Use when building or modifying a page that lists/displays data, adding a table, wiring…

Cratis/AI · 93 tokens

toolbar

Use this skill when asked to add or build a canvas-style icon toolbar using the @cratis/components Toolbar component. Covers Toolbar, ToolbarButton, ToolbarSeparator, ToolbarSection, ToolbarContext, and ToolbarFanOutItem. Use whenever building tool panels, drawing tool selectors, zoom controls, or any icon-button…

Cratis/AI · 78 tokens

add-traces

Use this skill when asked to add OpenTelemetry tracing to a class in a Cratis Chronicle Kernel project. Produces Traces.cs companion files using the [Span] source-generator pattern from Cratis.Traces, registers IActivitySource as a keyed DI service, and injects it into the target class.

Cratis/AI · 73 tokens

auth-and-identity

Use this skill for authentication, authorization, or identity in a Cratis Arc project — backend, frontend, or both. Covers identity providers (IProvideIdentityDetails), protecting commands/queries with authorization attributes, Microsoft Identity Platform, connecting backend identity to React, multi-tenant identity…

Cratis/AI · 88 tokens

cratis-specs-csharp

Step-by-step guidance for writing C# specs in Cratis with BDD Specification by Example — the Establish/Because/should pattern, for/when/and folder hierarchy, reusable given/ contexts, NSubstitute mocking, and the in-process scenario family. Use when writing C# unit or integration specs or structuring the for/when/and…

Cratis/AI · 101 tokens

cratis-fundamentals-concept

Create strongly typed Cratis domain values with ConceptAs and Chronicle event-source identities with EventSourceId . Use when a C# domain value has meaning beyond its primitive or when an identity is actually used as a Chronicle event-source/stream ID. Do not use for enums, DTO-only transport values, arbitrary…

Cratis/AI · 82 tokens