Home / kurrent-io / kcap-cli · kcap/skills/eval-watch/SKILL.md · GitHub

eval-watch skillA

eval-watch is agent-read markdown (skill) from kurrent-io/kcap-cli: 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 Capacitor analytics for exactly the sessions that import created, summarizes the first three completed evals, links to the results and offers the guided tour. Not for browsing evals in general — that is the analytics or guided-tour skill..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Eval watch

You follow ONE import: the sessions listed in a handoff file `kcap setup` wrote. Every query you
issue names only those sessions — never a repo-wide or tenant-wide read, and never a query without
an `IN (...)` or `session_id = '...'` bound to this cohort. If a response ever includes a row for a
session id outside the cohort, discard that row: never count it, link it, or mention it.

## The safety rule — read this first

Three grammars gate everything below:
- **Run id** (a `(run: <id>)` token, and the file's own `run_id`): `^[0-9a-f]{32}$`.
- **Session id** (`session_ids`, `foreground_succeeded_ids`, and any id you place in a query):
  `^[A-Za-z0-9_-]{1,128}$`.
- **Repo hash** (the `repo_hash` field an analytics response returns, used only in the repo-scoped
  link form): `^[0-9a-f]{16}$`. A `repo_hash` that fails this never reaches a link — fall back to
  the no-repo-hash link form (section 7).

The `kcap-analytics` MCP takes raw SQL text with no parameter binding, so the session-id grammar is
the SQL-safety boundary, not just a format check. The class excludes quote, backslash, whitespace
…

Read the whole file at its exact version.

How to install

Latest version
mdr add kurrent-io/kcap-cli/eval-watch@git:20260919.a0ad3f2
Exact content
mdr add kurrent-io/kcap-cli/eval-watch@sha256:f1787311e51d2b74

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_muprcrqerb4nxbxs.svg)](https://markdownregistry.com/a/art_muprcrqerb4nxbxs)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260919.a0ad3f2 latest2026-09-19 a0ad3f2 12,349 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (12349 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

GitHub

kurrent-io/kcap-cli · 30 stars · license NOASSERTION · pushed 2026-09-23 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_muprcrqerb4nxbxs
GET https://markdownregistry.com/api/v1/resolve?ref=kurrent-io/kcap-cli/eval-watch
GET https://markdownregistry.com/api/v1/blob/f1787311e51d2b74f61fce2c6ff1d13463b3a54cc52838b10c0b22df71dabaaa

Your agent 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.

More from kurrent-io/kcap-cli

CLAUDE.md claude
kurrent-io/kcap-cli · CLAUDE.md
git:20260922.b514d94 · audit A · 30 stars
agent-flows skill
kurrent-io/kcap-cli · kcap/skills/agent-flows/SKILL.md · This skill should be used ONLY when the user explicitly asks to run a structured agent *flow* by name or definition id…
git:20260922.ca8d4e5 · audit A · 30 stars
disable skill
kurrent-io/kcap-cli · kcap/skills/disable/SKILL.md · This skill should be used when the user asks to "disable recording", "stop recording", "delete this session", "don't…
git:20260603.b07d25b · audit A · 30 stars
errors skill
kurrent-io/kcap-cli · kcap/skills/errors/SKILL.md · This skill should be used when the user asks to "show errors", "extract errors", "what went wrong", "find tool errors"…
git:20260603.b07d25b · audit A · 30 stars
guided-tour skill
kurrent-io/kcap-cli · kcap/skills/guided-tour/SKILL.md · Guided tour of Kurrent Capacitor for someone who has it installed but does not yet know what it does for them — "what…
git:20260727.660b79d · audit A · 30 stars
hide skill
kurrent-io/kcap-cli · kcap/skills/hide/SKILL.md · This skill should be used when the user asks to "hide this session", "make this private", "hide session", "owner only"…
git:20260603.b07d25b · audit A · 30 stars
plans skill
kurrent-io/kcap-cli · kcap/skills/plans/SKILL.md · This skill should be used whenever you write or read a plan, spec or design document, when you start executing a plan…
git:20260915.7b4a618 · audit A · 30 stars
recap skill
kurrent-io/kcap-cli · kcap/skills/recap/SKILL.md · This skill should be used to read, search, or recall past Kurrent Capacitor sessions. Triggers include: "read a…
git:20260903.15a253a · audit A · 30 stars
review-flows skill
kurrent-io/kcap-cli · kcap/skills/review-flows/SKILL.md · This skill should be used ONLY when the user explicitly asks to run a structured review *flow* — e.g. "start a review…
git:20260922.ca8d4e5 · audit A · 30 stars
suggest-review-flow skill
kurrent-io/kcap-cli · kcap/skills/suggest-review-flow/SKILL.md · Use this skill when implementation is complete — a feature or bugfix is functionally finished, tests pass, or you are…
git:20260822.462801e · audit A · 30 stars
validate-plan skill
kurrent-io/kcap-cli · kcap/skills/validate-plan/SKILL.md · This skill should be used when the user asks to "validate plan", "verify plan", "check plan completion", "did I finish…
git:20260915.7b4a618 · audit A · 30 stars
work-items skill
kurrent-io/kcap-cli · kcap/skills/work-items/SKILL.md · This skill should be used when you are planning or discovering the SHAPE of a work item — that it breaks into sub-tasks…
git:20260916.2afadb2 · audit A · 30 stars

Every file in kurrent-io/kcap-cli

Browse by kind, by grade A, or by owner.