jevflow SKILL.md skillA

jevflow from parth1811/jevflow is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add parth1811/jevflow/jevflow@git:20261005.226e8c5

Pins git:20261005.226e8c5 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
parth1811/jevflow
Path
skills/jevflow/SKILL.md
Versions recorded
4
Latest version
git:20261005.226e8c5, committed Oct 5, 2026
First version recorded
Sep 24, 2026
Size
4,263 bytes
Repository stars
11
License
MIT

How to work inside a Jevflow-tracked session. Use when a Jevflow context block or a "[jevflow]" Stop instruction appears, when the user asks to keep a long task on track toward a goal, or when they mention flow.json, phases, or the Jevflow supervisor.

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

# Working with Jevflow

Jevflow tracks a session against a flow in `.jevflow/flow.json`: a goal and ordered phases, each with a `done_when` sentence and often a shell `check`. When you try to stop, a Stop hook runs the checks, asks Jev (a calibrated judgment model) where the work is, and a fixed policy decides whether you may stop.

## When a `[jevflow]` instruction blocks your stop

- Treat it as the next instruction. Do the concrete thing it names for the named phase.
- If it quotes failing check output, fix the cause shown there. Run the check command yourself before claiming the phase is done.
- "You said the work is done, but it is not" means a check still fails. Do not repeat the claim; make the check pass.
- "You are looping" means your last approach is not working. Re-read the goal and change approach, not just parameters.
- "Regression" means a phase that was done now fails its check. Fix that first.
- Never edit `.jevflow/state.json` or `.jevflow/flow.json` to get past a block. Only Jevflow code writes state. Changing the flow is a user decision.

## Starting and checking

- `/jevflow:init <goal>` writes a flow (starts in `warn` mode, which reports but does not block).
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add parth1811/jevflow/jevflow@sha256:6b795463656ffe3c

The line at the top of this page pins the label git:20261005.226e8c5, 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_bgnzwciggzpwi2ts.svg)](https://markdownregistry.com/a/art_bgnzwciggzpwi2ts)

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

Versions

The registry has recorded 4 versions of this file, between Sep 24, 2026 and Oct 5, 2026, about one every 4 days.

versioncommittedcommitsizeaudit
git:20261005.226e8c5 latest2026-10-05 226e8c5 4,263 BA view · diff
git:20260924.3f91ea22026-09-24 3f91ea2 3,753 BA view · diff
git:20260924.93485742026-09-24 9348574 2,739 BA view · diff
git:20260924.67ad4c52026-09-24 67ad4c5 2,064 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 (4263 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

parth1811/jevflow · 11 stars · license MIT · pushed 2026-10-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_bgnzwciggzpwi2ts
GET https://markdownregistry.com/api/v1/resolve?ref=parth1811/jevflow/jevflow
GET https://markdownregistry.com/api/v1/blob/6b795463656ffe3c96f45c2835bde6ce91eea74ff86c7440a9a80aeadf54502f

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.

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