Do these 3 things before closing this tab:
1Clear out junk files and repair common Windows errors2Fix the driver behind crashes, sound loss and screen glitches3Repair Windows errors before they cause bigger problemsiTechGuides is reader-supported. When you buy through links on our site, we may earn an affiliate commission. As an Amazon Associate I earn from qualifying purchases. Learn more
Not automatically. If you change a helper script, reference, template, or other file in an agent-skill package, earlier test evidence may no longer describe the package you plan to release—even when SKILL.md is unchanged. TraceMantle helps track those package changes and compare supplied evaluation evidence with a trusted policy. It analyzes files and evidence; it does not run the skill or prove how an agent will perform in a live environment.
Why SkillCheck became TraceMantle
Project maintainer Brad Kinnard announced the rename from SkillCheck to TraceMantle on September 13, 2026. He said the former name conflicted with another project, while TraceMantle better reflected the expanded goal: checking a skill package and examining whether evidence used to approve a version still applies. The project retains skill-file validation and adds bundle tracking and evidence comparison. Read Kinnard’s dated explanation.
![Claude AI for Beginners Bible: [5 in 1] The Ultimate Guide to Automate Your Work, Save Hours Every Week, and Use AI for Real-World Results](https://m.media-amazon.com/images/I/415+fSJacsL._SL160_.jpg)
An agent skill is not necessarily just its instruction file. A package can also contain helper scripts, reference documents, templates, and schemas. Those supporting files can affect behavior, so a passing report tied to an earlier package may not cover a changed release candidate.
What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
How TraceMantle checks whether evidence still fits
- Validate the skill files. TraceMantle checks matters including
SKILL.mdfrontmatter, file references, size limits, and compatibility advice against the Agent Skills specification. - Track the package. A manifest records package files and content fingerprints. This can reveal a change to a supporting file even when the main instruction file has not changed.
- Import evaluation evidence. It supports a version-pinned Promptfoo export format and preserves the original export alongside information about evaluated inputs, configuration, checks, and execution context.
- Compare evidence with the release candidate. TraceMantle checks the supplied evidence against the candidate package and an approved policy. It can report changed inputs, incompatible or missing evidence, and checks that should be rerun.
- Keep the policy independent. The policy is read from a selected trusted Git revision. The candidate package cannot replace that policy or make required checks optional. A passing result in an imported report is not automatically trusted: the project owner or trusted automation must validate it against the policy.
The key question is not simply whether a report says “pass.” It is whether the report covers the package inputs that matter under the trusted policy. If a changed file is outside the evidence’s coverage, the previous result does not establish that the new bundle passes.
#1 Best Overall
What pass, fail, and unknown mean
A failed check is different from missing or unsuitable evidence. TraceMantle uses unknown when the available evidence does not establish a pass. Treat that as an unresolved release check—not as approval, and not as proof that the skill itself failed.
- Pass: Evidence satisfies the applicable policy for the relevant inputs.
- Fail: A check did not meet its required result.
- Unknown or unsuitable evidence: The available material cannot establish the required pass, so the gap needs to be addressed.
What TraceMantle does not prove
TraceMantle analyzes files and supplied evidence; it does not execute agent skills or evaluators. Static validation and imported model judgments therefore cannot prove that an agent will perform a task correctly in a live environment.
Dependency analysis also has limits: it cannot infer every runtime dependency or arbitrary programming-language import. Trusted checks need accurate declarations of their inputs; when coverage is incomplete, further evaluation is needed. A structurally valid skill is not, by itself, evidence of successful real-world performance.
Ways to use the project
The project describes TraceMantle as a local Python CLI and library. Its repository and package listing also describe PyPI installation, a composite GitHub Action, a pre-commit hook, and a Python API. The listing specifies Python 3.10 or later and shows a GitHub Action pinned to a release. Check the current repository and release record for commands and supported versions before adopting them.
Project maintainers report 1,407 tests, CI across Python 3.10 through 3.13, and CI on Linux, macOS, and Windows in the project listing. These are project-reported test and CI figures, not independent results or measures of live agent performance.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.Version details depend on the snapshot
Kinnard’s September 13, 2026 article described version 1.6.0 as published and noted two defects still to address: Markdown dependency detection and numeric JSON input handling. The repository and package listing surfaced version 1.6.1, which they describe as correcting dependency discovery across Markdown headings and rejecting numeric overflow in evidence imports. These are different dated snapshots; consult the current changelog and release record for present status.
Quick Recap
Best Value
Rank #4
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
