watch-admin

watch-admin is a skill for Claude Code, Codex from flurdy/agent-skills. It costs 46 tokens per session (2,521 once invoked), scanned A, original, MIT.

A bounded watcher for a specific project workspace and the current user's unfinished Jira work, reporting material changes in local and assigned work.

In plain words
What is it for?
It helps monitor Git, Beads, and Jira transitions and can print one recommendation for a person to carry out manually, but only in the approved isolated test process.
Why use it?
It provides unattended status reporting while remaining read-only and avoiding automatic follow-up actions.

Skill for Claude CodeCodex

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

Made for: Claude Code, Codex.

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-admin

README.md
[![agentmods](https://agentmods.dev/badge/skills/flurdy/agent-skills/watch-admin.svg)](https://agentmods.dev/skills/flurdy/agent-skills/watch-admin)
Your own site
<a href="https://agentmods.dev/skills/flurdy/agent-skills/watch-admin"><img src="https://agentmods.dev/badge/skills/flurdy/agent-skills/watch-admin.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,521 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 $0.00046 $0.02521
Opus 5 $0.00023 $0.01260
Sonnet 5 $0.00009 $0.00504
Haiku 4.5 $0.00005 $0.00252

Measured 4d ago against content hash 94addc56bc2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

watch-admin 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 4d ago.

The scan reads SKILL.md. This mod also ships 7 executable files (scripts/collect.py, scripts/jira_adapter.py, scripts/reducer.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/watch-admin/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Watch workspace administration

Run one bounded protocol-v1 watch over two explicitly separate evidence domains:

  • [workspace]: local Git and proven owning Beads stores for a validated project workspace;
  • [assigned Jira portfolio]: issues assigned to the current user whose status category is not Done.

The watcher is unattended and structurally read-only. It reports normalized transitions and may print one paste-ready attended workflow recommendation. It never runs that workflow.

UAT candidate gate

This skill remains no-go for ordinary use. It may run only in the approved isolated BLC UAT process at /home/ivar/Code/blc/workspace, with WATCH_ADMIN_UAT=1 and WATCH_ADMIN_UAT_WORKSPACE set to that exact absolute path. The 2026-08-07 BLC UAT returned no-go; no further run is authorized without a newly approved plan. That process must be a fresh dedicated Pi session launched on the configured standard model and thinking level and invoke Pi's canonical /skill:watch-admin command. The preflight rejects missing UAT authorization or route telemetry, the wrong workspace, a resumed session, a non-standard route, or any provider, model, or thinking change before the watch starts. Do not bypass that failure or retry on a more favourable route.

Usage

/skill:watch-admin                 # adaptive, at most 10 ticks
/skill:watch-admin --ticks N       # N from 1 through 96
/skill:watch-admin --until HH:MM   # future local wall-clock deadline

Accept exactly one optional bound. Reject duplicate, combined, unknown, non-integer, out-of-range, or past-deadline arguments. There is no unbounded mode and no Claude scheduling fallback.

Safety boundary

This skill and every tick are read-only. Never edit files, change Git or Beads state, mutate Jira, invoke GitHub, publish communication, alter runtime configuration, ask a question, or invoke another skill. Do not call /tracking-sweep, /project-brief, /backlog-groom, or /triage; material evidence may render one of those literal commands as a recommendation only.

Read the full file on GitHub · 157 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 157 lines · 46 tokens per session scan A 94addc56bc2f

Subscribe to this mod's changes

watch-admin is a skill published in the GitHub repository flurdy/agent-skills (7 stars, last pushed 6d ago), licensed MIT. It adds 46 tokens to every session and 2,521 once invoked, about $0.0002 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

convex-add

Add a capability to the CURRENT Convex app — consults the served Convex capability catalog for always-current procedures (billing, crons, auth, agent, search, …); falls back to built-in hosting or @convex-dev component search. TRIGGER when the user runs /add, or asks to add hosting/publishing or any backend capability…

openclaw/clawhub · 81 tokens

twitter-reader

Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…

himself65/finance-skills · 161 tokens

chenhao-limit-up

Use when evaluating A-share limit-up (涨停板) setups through Chen Hao's sentiment and momentum lens: market emotion cycles, board strength, follow-through, and short-term aggressive momentum trading.

questflowai/investorskills · 44 tokens

trading-risk-gate

Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.

winstonkoh87/Athena-Public · 53 tokens

cwv-optimizer

Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…

adobe/skills · 112 tokens

multi-expert-analyzer

针对通用问题进行多领域专家联合分析, 综合稿产生前必经 fact-checker 与 red-team 两道独立校验。适用场景: 用户提出跨领域或不确定领域的复杂问题, 需要从多个专家角度分别搜证并相互校验后综合成文, 例如该不该买房、该不该跳槽、是否进入某个赛道等。触发关键词: 多角度分析、专家分析、综合分析、多视角、跨领域分析、从不同角度看、深度分析。问题只属于单一明确领域时, 优先使用该领域的专门 skill, 例如纯财务用 finance-core-analysis、纯技术用 software-architect。输出 (全部 markdown 保存到当前项目 markdown/ 目录): (1) 每位专家的中间分析稿…

digoal/blog · 292 tokens