agentpulse: Skill for Claude Code

.claude/skills/release-regression-check/SKILL.md

release-regression-check is a skill for Claude Code from prove-ai/agentpulse. It costs 54 tokens per session (310 once invoked), scanned A, original, MIT.

A workflow for comparing two software versions to find whether a release caused a meaningful regression. A regression is a new problem or loss of quality introduced by a change.

In plain words
What is it for?
Use it to compare named versions, check a baseline against the newest version, or find which release broke an outcome. It reports the critical drift, changed metrics, affected result, and possible follow-up checks.
Why use it?
It helps distinguish a real outcome-breaking problem from an ordinary metric change. It also identifies the release that introduced the drift rather than blaming the entire period between versions.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is prove-ai/agentpulse's own configuration. It tells Claude Code how to work on agentpulse itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agentpulse configures →

Reuse

Borrowing it

Nothing to install: this file belongs to prove-ai/agentpulse. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/prove-ai/agentpulse/main/.claude/skills/release-regression-check/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/prove-ai/agentpulse

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 release-regression-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/prove-ai/agentpulse/release-regression-check.svg)](https://agentmods.dev/skills/prove-ai/agentpulse/release-regression-check)
Your own site
<a href="https://agentmods.dev/skills/prove-ai/agentpulse/release-regression-check"><img src="https://agentmods.dev/badge/skills/prove-ai/agentpulse/release-regression-check.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 310 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 $0.00054 $0.00310
Opus 5 $0.00027 $0.00155
Sonnet 5 $0.00011 $0.00062
Haiku 4.5 $0.00005 $0.00031

Measured 8d ago against content hash 4c05133ba85b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

release-regression-check 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 8d 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/release-regression-check/SKILL.md · 24 lines

What it actually says

Release regression check

Answer "did this release regress?" and attribute the drift to the release that caused it.

Steps

  1. Call get_version_comparison:
    • No versions named → default (baseline → newest).
    • Two named (e.g. "v3 vs v4") → base_version + target_version.
    • "which release broke it" / "across all versions" → across_all=True.
  2. Lead with the critical drift, stating which version introduced it (introduced_in).
  3. Report the metrics that changed for that root and the outcome it broke (e.g. clean-finish rate).
  4. Only mention intended changes if asked (include_intended=True) — label them intended, not regressions. Hide low-confidence unless asked (include_low_confidence=True).
  5. If a critical drift is found, offer get_next_check_steps.

Principles

  • Always state which two versions were compared.
  • "Baseline vs newest" spans multiple releases — attribute to the release that introduced the drift, not the whole span.
  • A metric moving ≠ a regression. Only outcome-breaking, high-confidence drift is critical.
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. 8d ago First seen · 24 lines · 54 tokens per session scan A 4c05133ba85b

Subscribe to this mod's changes

release-regression-check is a skill published in the GitHub repository prove-ai/agentpulse (11 stars, last pushed 3d ago), licensed MIT. It adds 54 tokens to every session and 310 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 2026-08-30.