at-risk-detection

at-risk-detection is a skill for Claude Code from britt/agent-skills. It costs 61 tokens per session (1,394 once invoked), scanned A, original, MIT.

A project-health checker that reviews GitHub issues and pull requests, which are proposed code changes, for warning signs such as inactivity, blockers, deadline risk, large changes, or missing owners.

In plain words
What is it for?
Use it during sprint planning, standups, milestone reviews, backlog triage, or regular health checks to produce a severity-ranked list of risky work.
Why use it?
It helps teams spot work that may miss a deadline or remain stuck before the problem becomes harder to fix.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the agent-skills plugin — 28 skills shipped together

Good fit Use it during sprint planning, standups, milestone reviews, backlog triage, or regular health checks to produce a severity-ranked list of risky work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/britt/agent-skills/at-risk-detection
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.

Any agent
npx skills add britt/agent-skills --skill at-risk-detection
Clone the repo
git clone --depth 1 https://github.com/britt/agent-skills

Made for: Claude Code.

Or install agent-skills, the plugin that ships this one along with the rest of its 28 skills.

Its marketplace also offers this one on its own, as the plugin at-risk-detection/plugin install at-risk-detection after adding the marketplace above.

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 at-risk-detection

README.md
[![agentmods](https://agentmods.dev/badge/skills/britt/agent-skills/at-risk-detection/github.svg)](https://agentmods.dev/skills/britt/agent-skills/at-risk-detection)
Your own site
<a href="https://agentmods.dev/skills/britt/agent-skills/at-risk-detection"><img src="https://agentmods.dev/badge/skills/britt/agent-skills/at-risk-detection/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.

agentmods 80×15 button for at-risk-detection

Your own site · 80×15
<a href="https://agentmods.dev/skills/britt/agent-skills/at-risk-detection"><img src="https://agentmods.dev/badge/skills/britt/agent-skills/at-risk-detection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,394 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00061 $0.01394
Opus 5 $0.00030 $0.00697
Sonnet 5 $0.00012 $0.00279
Haiku 4.5 $0.00006 $0.00139

Measured 9d ago against content hash 70a98b7bbcc8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

at-risk-detection 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 9d 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.

skills/at-risk-detection/SKILL.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

At-Risk Detection Skill

Proactively scan GitHub issues and pull requests to identify at-risk items before they become problems.

When to Use

Activate when:

  • Starting a new sprint or planning session
  • During standup to identify blockers
  • Weekly health checks of the project
  • When asked about project health or status
  • Before milestone deadlines
  • When triaging backlog items

Analysis Approach

Prerequisite: Requires the gh CLI. Fetch data with, e.g.:

gh issue list --state open --limit 30 --json number,title,updatedAt,labels,assignees,milestone,comments
gh pr list --state open --json number,title,updatedAt,additions,deletions,isDraft,reviewRequests

Quick Mode (Default)

Fetch the 30 most recent open issues:

  • Fast (seconds)
  • Good for daily checks
  • May miss older stale items

Comprehensive Mode

Fetch ALL open issues by paginating:

  • Thorough analysis
  • Slower for large repositories
  • Best for milestone reviews

Risk Types and Detection Heuristics

Stale Items

Signal: No activity for extended period Default Threshold: 14 days for issues, 3 days for PRs awaiting review Severity Escalation:

  • Warning: > threshold days since last activity
  • Critical: > 2x threshold days since last activity

How to detect: Check updated_at field on each issue/PR. Calculate days since last update.

Blocked Work

Signals:

  • Has labels matching: blocked, waiting, on-hold, waiting-for-response
  • Body contains: "blocked by #", "waiting on", "depends on", "blocked until"
  • PR is in draft status
  • PR has merge conflicts (if detectable from comments)

How to detect: Check labels array for blocking keywords. Search body text for blocking phrases.

Deadline Risks

Signal: Milestone deadline approaching or overdue Severity Levels:

  • Critical: Overdue or due within 2 days
  • Warning: Due within 7 days

How to detect: Check if issue has a milestone with a due_on date. Compare to current date.

Read the full file on GitHub · 182 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. 9d ago First seen · 182 lines · 61 tokens per session scan A 70a98b7bbcc8

Subscribe to this mod's changes

at-risk-detection is a skill published in the GitHub repository britt/agent-skills (5 stars, last pushed 7d ago), licensed MIT. It adds 61 tokens to every session and 1,394 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