agent-flows 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.

agent-flows from kurrent-io/kcap is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add kurrent-io/kcap/agent-flows@git:20261029.ab14ff3

Pins git:20261029.ab14ff3 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/agent-flows/SKILL.md
Versions recorded
5
Latest version
git:20261029.ab14ff3, committed Oct 29, 2026
First version recorded
Oct 19, 2026
Size
32,395 bytes
Repository stars
31
License
a license file GitHub does not identify

Use this skill to drive a structured agent *flow*: a separate hosted participant agent runs a definition from the server's flow catalogue and iterates with you until sign-off. Use it when the user names a flow or definition id ("run the code-review flow", "start a flow", "use flow definition X"), when the user accepts a flow you offered, or when you are about to offer one listed under "Flows you may offer" in your session context because its when-to-use applies. Before starting a flow, call…

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

# Agent Flows

Use the `kcap mcp flows` MCP tools (`list_flow_definitions`, `get_flow_definition`, `start_flow`, `send_to_participant`, `get_flow_status`, `close_flow`) to run a structured agent **flow**: your work is handed to a **separate, hosted participant agent** driven by a flow definition from the server's catalog, which returns a result (kind `findings` with the participant's result text, or `clean`); you address a `findings` result and keep iterating until the clean signal. This is a deliberate, heavier workflow — use it when the user asks for a flow or accepts one you offered, never on your own initiative.

## Long rounds are normal

`round_timeout` is an **inactivity** bound, not a wall-clock cap: a round only fails for taking too long if the participant goes genuinely quiet for that whole stretch — an actively-working participant can legitimately run a round for a long time. If a status check (or `start_flow`/`send_to_participant`) returns the benign "Flow still running" text, that is an expected outcome on a long round, not a problem — re-enter the wait with `get_flow_status(flow_run_id, wait: true)`, which blocks (via bounded, internally-retried checks — never a raw…
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add kurrent-io/kcap/agent-flows@sha256:8b5fe52cdca7cc81

The line at the top of this page pins the label git:20261029.ab14ff3, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ynogpepgu44so6gt.svg)](https://markdownregistry.com/a/art_ynogpepgu44so6gt)

0 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Oct 19, 2026 and Oct 29, 2026, about one every 3 days.

versioncommittedcommitsizeaudit
git:20261029.ab14ff3 latest2026-10-29 ab14ff3 32,395 BA view · diff
git:20261020.bf6d98a2026-10-20 bf6d98a 32,056 BA view · diff
git:20261020.059935c2026-10-20 059935c 31,823 BA view · diff
git:20261019.02040a92026-10-19 02040a9 31,306 BA view · diff
git:20261019.31efd582026-10-19 31efd58 30,838 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the 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 (32395 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 · 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_ynogpepgu44so6gt
GET https://markdownregistry.com/api/v1/resolve?ref=kurrent-io/kcap/agent-flows
GET https://markdownregistry.com/api/v1/blob/8b5fe52cdca7cc81073455ae9cad1a266edc6c0512543d43a5cbe8bda3f11eea

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.

More from kurrent-io/kcap

CLAUDE.md CLAUDE.md file
kurrent-io/kcap · CLAUDE.md
git:20261031.6163a78 · audit A · 31 stars
kcap-recording SKILL.md skill
kurrent-io/kcap · kcap/muse-assistant/kcap-recording/SKILL.md · Record this user's Muse chats into kcap as private sessions, with their explicit written consent, through `kcap…
git:20261020.c6e5247 · audit A · 31 stars
connect-capacitor SKILL.md skill
kurrent-io/kcap · kcap/skills/connect-capacitor/SKILL.md · Compatibility redirect to the connect-kcap skill for previously shared links.
git:20261020.c6e5247 · audit A · 31 stars
connect-kcap SKILL.md skill
kurrent-io/kcap · kcap/skills/connect-kcap/SKILL.md · This skill should be used when the user asks to "connect kcap", "set up kcap", "install kcap", "log in to kcap"…
git:20261101.c9b59c2 · audit A · 31 stars
disable SKILL.md skill
kurrent-io/kcap · 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 · 31 stars
errors SKILL.md skill
kurrent-io/kcap · 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:20261020.c6e5247 · audit A · 31 stars
eval-watch SKILL.md skill
kurrent-io/kcap · kcap/skills/eval-watch/SKILL.md · Follow a kcap import that setup just started and the evals landing on it — "Follow my kcap import" (the prompt `kcap…
git:20261020.c6e5247 · audit A · 31 stars
guided-tour SKILL.md skill
kurrent-io/kcap · kcap/skills/guided-tour/SKILL.md · Guided tour of kcap for someone who has it installed but does not yet know what it does for them — "what does kcap do…
git:20261026.d563619 · audit A · 31 stars
hide SKILL.md skill
kurrent-io/kcap · 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:20261020.c6e5247 · audit A · 31 stars
pages SKILL.md skill
kurrent-io/kcap · kcap/skills/pages/SKILL.md · This skill should be used whenever the user asks for an artifact, a page, a report, a dashboard, a comparison, a mockup…
git:20261028.50581cb · audit A · 31 stars
plans SKILL.md skill
kurrent-io/kcap · 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:20261020.c6e5247 · audit A · 31 stars
recap SKILL.md skill
kurrent-io/kcap · kcap/skills/recap/SKILL.md · This skill should be used to read, search, or recall past kcap sessions. Triggers include: "read a previous session"…
git:20261031.5a0aa28 · audit A · 31 stars

Every file in kurrent-io/kcap

Other files named agent-flows

agent-flows SKILL.md skill
geekfujiwara/codeappsdevelopmentstandard · .github/skills/agent-flows/SKILL.md · Copilot Studio 新 UI の Agent flows / Workflows を構築・公開・検証する。Dataverse レコード作成/更新トリガーから既存の発行済み Copilot Studio v2 を Agent…
git:20261019.d75ad2d · audit A · 76 stars
agent-flows SKILL.md skill
kurrent-io/kcap-cli · kcap/skills/agent-flows/SKILL.md · Use this skill to drive a structured agent *flow*: a separate hosted participant agent runs a definition from the…
git:20261029.ab14ff3 · audit A · 31 stars

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