pr-threshold

pr-threshold is a skill for Claude Code, Codex from WellApp-ai/Well. It costs 13 tokens per session (1,099 once invoked), scanned A, original, MIT.

A review checkpoint that tracks how much code has accumulated before opening a pull request, which is a request for human review of changes. It checks code volume, files, commits, risk, and completion.

In plain words
What is it for?
Use it after commits to measure changed lines, files, commit count, review risk, and planned-scope completion.
Why use it?
It helps prevent changes from becoming too large or complex to review effectively. It signals when the accumulated work is ready for careful human inspection.

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/wellapp-ai/well/pr-threshold
Any agent
npx skills add WellApp-ai/Well --skill pr-threshold
Clone the repo
git clone --depth 1 https://github.com/WellApp-ai/Well

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 pr-threshold

README.md
[![agentmods](https://agentmods.dev/badge/skills/wellapp-ai/well/pr-threshold.svg)](https://agentmods.dev/skills/wellapp-ai/well/pr-threshold)
Your own site
<a href="https://agentmods.dev/skills/wellapp-ai/well/pr-threshold"><img src="https://agentmods.dev/badge/skills/wellapp-ai/well/pr-threshold.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,099 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 $0.00013 $0.01099
Opus 5 $0.00006 $0.00549
Sonnet 5 $0.00003 $0.00220
Haiku 4.5 $0.00001 $0.00110

Measured 5d ago against content hash 426ed3ab3442, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pr-threshold 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 5d 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.

cursor-rules/skills/pr-threshold/SKILL.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Threshold Skill

Monitor accumulated commits and metrics to determine when a PR should be pushed for human review. Prevents PRs from becoming too large or complex for effective review.

When to Use

  • After each successful git commit
  • During Agent Mode commit-level workflow
  • Manually with "use pr-threshold skill"

Thresholds

Metric Trigger Value Rationale
Lines of Code > 300 Human cognitive limit
Files Changed > 10 Context switching cost
Commits > 5 Review complexity
Risk Score HIGH Needs careful review
Scope Completion 100% Feature complete

Phase 1: Gather Metrics

1.1 Lines of Code

git diff origin/develop --stat | tail -1

Extract: insertions + deletions

1.2 Files Changed

git diff origin/develop --name-only | wc -l

1.3 Commit Count

git rev-list origin/develop..HEAD --count

1.4 Risk Score

Sum of risk from pr-review across all commits:

  • LOW = 1
  • MEDIUM = 2
  • HIGH = 3

1.5 Scope Completion

From Commit Plan:

  • Total commits planned: N
  • Commits completed: M
  • Completion: M/N * 100%

Phase 2: Evaluate Thresholds

## PR Threshold Check

| Metric | Current | Threshold | Status |
|--------|---------|-----------|--------|
| Lines of Code | [N] | 300 | OK/CROSSED |
| Files Changed | [N] | 10 | OK/CROSSED |
| Commits | [N] | 5 | OK/CROSSED |
| Risk Score | [N] | HIGH | OK/CROSSED |
| Scope Completion | [N]% | 100% | OK/CROSSED |

Phase 3: Determine Action

CONTINUE (No threshold crossed)

## Verdict: CONTINUE

No thresholds crossed. Proceeding to next commit.

### Current Accumulation:
- LOC: [N]/300
- Files: [N]/10
- Commits: [N]/5
- Scope: [N]%

### Next Commit:
[Name of next commit from plan]

TRIGGER_PR (Threshold crossed)

## Verdict: TRIGGER_PR

**Threshold crossed:** [Which metric(s)]

### Recommendation:
Push PR now for human review before continuing.

### PR Scope:
- Commits: [List of commit names]
- Total LOC: [N]
- Files: [N]
- Risk: [LOW/MEDIUM/HIGH]

### Remaining Work:
- Commits left: [N]
- Features incomplete: [List]

**Proceed to push-pr mode?** (Yes / Continue anyway)

Read the full file on GitHub · 208 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. 5d ago First seen · 208 lines · 13 tokens per session scan A 426ed3ab3442

Subscribe to this mod's changes

pr-threshold is a skill published in the GitHub repository WellApp-ai/Well (340 stars, last pushed 29d ago), licensed MIT. It adds 13 tokens to every session and 1,099 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 2026-08-30.