Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/PramodDutta/qaskillsnpx agentmods add skills/pramoddutta/qaskills/changelog-test-mapperWrote 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/pramoddutta/qaskills/changelog-test-mapper)<a href="https://agentmods.dev/skills/pramoddutta/qaskills/changelog-test-mapper"><img src="https://agentmods.dev/badge/skills/pramoddutta/qaskills/changelog-test-mapper/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/pramoddutta/qaskills/changelog-test-mapper"><img src="https://agentmods.dev/badge/skills/pramoddutta/qaskills/changelog-test-mapper.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 | $0.00028 | $0.08101 |
| Opus 5 | $0.00014 | $0.04050 |
| Sonnet 5 | $0.00006 | $0.01620 |
| Haiku 4.5 | $0.00003 | $0.00810 |
Grade A, and why
Changelog Test Mapper scanned grade A with 1 finding 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 6d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
import { execSync } from 'child_process'; How it starts
The opening of the file, as written. The whole thing — 975 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Changelog Test Mapper
Every user-facing change in a software release should have corresponding test coverage that verifies the change works as intended. In practice, this mapping between changelog entries and test cases is rarely maintained, leading to releases where features ship without adequate verification and bug fixes lack regression tests. The Changelog Test Mapper bridges this gap by programmatically analyzing changelog entries, release notes, and commit histories, then mapping them to existing test cases and identifying coverage gaps. This skill covers the full pipeline: parsing changelogs in various formats, extracting change metadata, building a bidirectional mapping between changes and tests, scoring coverage completeness, and integrating the analysis into release workflows to prevent untested changes from reaching production.
Core Principles
1. Every Shipped Change Deserves a Test
The fundamental premise of changelog-test mapping is that if a change is important enough to appear in the changelog, it is important enough to have a test. Bug fixes need regression tests. New features need functional tests. Performance improvements need benchmark tests. Changes without tests are unverified promises.
2. Bidirectional Traceability
The mapping must work in both directions. Given a changelog entry, you should be able to find all related tests. Given a test, you should be able to find which changelog entries it covers. This bidirectional traceability enables both forward analysis ("is this release well-tested?") and backward analysis ("what does this test protect?").
3. Automation Over Manual Tracking
Manually maintaining a spreadsheet of change-to-test mappings does not scale. The mapping should be derived automatically from commit messages, PR descriptions, issue tracker links, and file-level change analysis. Manual annotations should supplement, not replace, automated discovery.
4. Coverage Scoring Is Contextual
Not all changelog entries need the same level of test coverage. A breaking API change requires more comprehensive testing than a documentation fix. The coverage scoring model must account for change severity, affected surface area, and historical defect rates.
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.
- 6d ago First seen · 975 lines · 28 tokens per session scan A e435254d521f
Changelog Test Mapper is a skill published in the GitHub repository PramodDutta/qaskills (220 stars, last pushed 10d ago), licensed MIT. It adds 28 tokens to every session and 8,101 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
am-command-build
Implement the next task incrementally — build, test, verify, commit.
merge-check
Xcode-specific pre-merge gate — archive build (catches strict-concurrency/MainActor errors debug builds miss), app-extension Info.plist check, SwiftLint — spawned in parallel. Trigger on Apple/Xcode merge intent specifically ("merge this iOS branch", "archive check before merge", "is this ready for TestFlight"); a…
husky-test-coverage
Sets up or verifies Husky git hooks to enforce test coverage above 80% (configurable) for Node.js/TypeScript projects. Activates when enforcing coverage through pre-commit hooks, verifying existing Husky/test setup, or configuring coverage thresholds for Jest, Vitest, or Mocha test runners.
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
chinese-commit-conventions
A Chinese-language guide to Conventional Commits, a format for writing consistent Git commit messages, plus related changelog, commit-checking, and commit-helper configuration.