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.
npx skills add WellApp-ai/Well --skill pr-thresholdgit clone --depth 1 https://github.com/WellApp-ai/WellWrote 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.
[](https://agentmods.dev/skills/wellapp-ai/well/pr-threshold)<a href="https://agentmods.dev/skills/wellapp-ai/well/pr-threshold"><img src="https://agentmods.dev/badge/skills/wellapp-ai/well/pr-threshold/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.
<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="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00013 | $0.01099 |
| Opus 5.5 | $0.00005 | $0.00440 |
| Sonnet 5.5 | $0.00003 | $0.00220 |
| Haiku 4.5 | $0.00001 | $0.00110 |
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 1mo 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.
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)
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.
- 1mo ago First seen · 208 lines · 13 tokens per session scan A 426ed3ab3442
pr-threshold is a skill published in the GitHub repository WellApp-ai/Well (345 stars, last pushed 6d ago), licensed MIT. It adds 13 tokens to every session and 1,099 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
hero-diff-highlight
A dark code editor reveals a red deletion then a green addition with a soft pulse. Function: PR / code-change explainer.
git-pr-workflows-git-workflow
Guide changes through code checks, testing, commits, and pull request preparation. Use when coordinating a complete Git workflow and verifying readiness for collaboration.
lean-review
CocoLean diff-scoped over-engineering audit — scans uncommitted git diff and applies five classification tags (delete/stdlib/native/yagni/shrink) to identify unnecessary surface area before commit.
review-gate
Use before an agent-produced diff is committed, pushed, opened as a PR, merged, landed, or applied to user files when explicit implementation approval is missing. Trigger for review gate, review pack, approve before landing, diff first then land, human approval, merge gate, commit gate, push gate, or PR readiness.…