eval-watch SKILL.md skillA
This file is byte-identical to the first copy the registry indexed. Same content hash, so the same checks give both the same grade.
eval-watch from kurrent-io/kcap is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add kurrent-io/kcap/eval-watch@git:20261020.c6e5247Pins git:20261020.c6e5247 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- kurrent-io/kcap
- Path
kcap/skills/eval-watch/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261020.c6e5247, committed Oct 20, 2026
- First version recorded
- Sep 19, 2026
- Size
- 12,864 bytes
- Repository stars
- 31
- License
- a license file GitHub does not identify
Follow a kcap import that setup just started and the evals landing on it — "Follow my kcap import" (the prompt `kcap setup` hands to your agent), "watch my import", "how is my import going", "are my evals done yet". Reads the handoff file setup wrote, polls the eval state of exactly the sessions that import created, waits for the sessions that imported while the user watched to be evaluated, summarizes their evals, links to the results and offers the guided tour. Works on every plan. Not for…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Eval watch
You follow ONE import: the sessions listed in a handoff file `kcap setup` wrote. Every lookup you
make names only those sessions — never a repo-wide or tenant-wide read. If a response ever carries
an entry for a session id outside the cohort, discard it: never count it, link it, or mention it.
Eval state comes from `get_session_evals` in the `kcap-sessions` MCP — never from the
`kcap-analytics` MCP, which is a paid feature the workspace may not have.
## The safety rule — read this first
Two grammars gate everything below:
- **Run id** (a `(run: <id>)` token, and the file's own `run_id`): `^[0-9a-f]{32}$`.
- **Session id** (`session_ids`, `foreground_succeeded_ids`, and any id you pass to a tool or put
in a link): `^[A-Za-z0-9_-]{1,128}$`.
An id that fails its grammar is **never** placed in a tool call, a path, or a link — reject it and
move on (section 2 below says what each layer's rejection does); never sanitize or escape an id
into something that would pass.
## 1. Find the run
- If the prompt carries a line `(run: <id>)`, `<id>` must match `^[0-9a-f]{32}$` before you use it
…Read the whole file at its exact version.
How to install
mdr add kurrent-io/kcap/eval-watch@sha256:d9defb0a21a48318The line at the top of this page pins the label git:20261020.c6e5247, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_ejlxdtl7sfffkcrx)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Sep 19, 2026 and Oct 20, 2026, about one every 8 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261020.c6e5247 latest | 2026-10-20 | c6e5247 | 12,864 B | A | view · diff |
| git:20261009.b643530 | 2026-10-09 | b643530 | 12,869 B | A | view · diff |
| git:20261008.cb95d0c | 2026-10-08 | cb95d0c | 12,078 B | A | view · diff |
| git:20260928.b543d27 | 2026-09-28 | b543d27 | 15,007 B | A | view · diff |
| git:20260919.a0ad3f2 | 2026-09-19 | a0ad3f2 | 12,349 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (12864 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
kurrent-io/kcap · 31 stars · license a license file GitHub does not identify · pushed 2026-11-04 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ejlxdtl7sfffkcrx GET https://markdownregistry.com/api/v1/resolve?ref=kurrent-io/kcap/eval-watch GET https://markdownregistry.com/api/v1/blob/d9defb0a21a48318c53af55d7e6e6182eb257678bdf5f1fb22d10d2defedc9b2
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.