Not in the top 1,000 by GitHub stars

grandamenium/jev-anything

Agent skill for designing, building, testing, and tuning bounded JEV decision layers

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

`SKILL.md`

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

448461f01a5a → 448461f01a5a

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 448461f01a5a

No earlier version was observed for comparison.

Compare on GitHub

View on GitHub Add to my skills

Verified commit 448461f01a5abb8b7026e2b2c222611ed18d2415

40GitHub stars

-1star in 7 days

1skill in this repository

0commits in 30 days

Heat

0.2

Star growth, last 7 daysNot available
Star growth, last 24 hoursNot available
Rank movement, last 7 daysNot available
Commits, last 30 daysNot available
Accounts asking about it through MCP, last 7 daysNot available
Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

30-day change not yet available: not enough history.

Individual skills in this repository

jev-anything /

How it works

jev-anything

When your agent uses it

Use when the user wants to add Jev (TypeSafe's System One decision model) to anything: a classifier, router, scorer, guardrail, extractor, or any "smart if-statement" in their code or workflow. Triggers include "add jev", "jev classifier", "route/score/classify/grade/guardrail with jev", "put a decision layer in", or "jev-anything". Works even when the user does not understand Jev yet: this skill makes you interrogate, educate, and plan with them first, then scaffold a working Jev layer through TypeSafe's direct API or OpenRouter.

What it loads into context

Frontmatter

158 tokens

Always available to the agent

SKILL.md

2,984 tokens

When the skill is activated

Reference documents

11,170 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Step 0: Read the references before you say anything technical
Step 1: Interrogate (understand what they actually want)
Step 2: Educate (be honest about fit, cost, and time)
Step 3: Plan (agree the exact question set before coding)
Step 4: Implement (drop the layer in)
Step 5: Verify (prove it before trusting it)
Step 6: Measure and optimize (do not skip this once it runs)
Guardrail default (carry this into every build)

Scripts executed separately

scaffolding/evaluate.py
scaffolding/examples/email_triage.py
scaffolding/examples/guardrail.py
scaffolding/examples/pr_risk_score.py
scaffolding/jev_client.py
scaffolding/jev_client.ts
scaffolding/make_rating_sheet.py

Files

CHANGELOG.mddoc4,545 bytes
EXAMPLE-PROMPTS.mddoc5,873 bytes
LICENSEasset1,094 bytes
PLAN-TEMPLATE.mddoc2,642 bytes
PROVENANCE.mddoc1,634 bytes
README.mddoc4,329 bytes
SKILL.mdcore12,462 bytes
START-HERE.mddoc4,878 bytes
references/01-what-jev-is.mddoc3,193 bytes
references/02-openrouter-decisions-api.mddoc7,002 bytes
references/03-fit-limits-cost-time.mddoc7,286 bytes
references/04-measure-and-optimize.mddoc5,780 bytes
scaffolding/.env.exampleasset232 bytes
scaffolding/evaluate.pyruns9,058 bytes
scaffolding/examples/email_triage.pyruns1,451 bytes
scaffolding/examples/guardrail.pyruns1,022 bytes
scaffolding/examples/pr_risk_score.pyruns1,200 bytes
scaffolding/jev_client.pyruns4,579 bytes
scaffolding/jev_client.tsruns2,919 bytes
scaffolding/make_rating_sheet.pyruns2,746 bytes

Read SKILL.md


# jev-anything

You are helping a user put a Jev decision layer into their software, even if they
do not understand Jev well. Your job is NOT to immediately write code. Your job is
to first understand Jev correctly, then work out with the user what they actually
need, then scaffold it through TypeSafe's direct API or OpenRouter.

## Step 0: Read the references before you say anything technical

Do not describe Jev, quote its cost, or write a call from memory. Read these first:

- `references/01-what-jev-is.md` - what Jev is and is not, the three decision
  primitives, how it actually works.
- `references/02-openrouter-decisions-api.md` - current TypeSafe direct access,

View the complete source on GitHub

Skills included

jev-anything

Repository facts

License: MIT
Created: Sep 24, 2026
Last pushed: Sep 24, 2026
Forks: 1
Open issues: 0
Project activity: Active

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 7, 2026

No broad tool permissions
No dangerous shell commands
82 network referencesin 8 files: references/02-openrouter-decisions-api.md:9 START-HERE.md:10 README.md:3 and 5 more
No hidden or obfuscated text
No instruction overrides
7 executable scriptsin 7 files: scaffolding/evaluate.py:1 scaffolding/examples/email_triage.py:1 scaffolding/examples/guardrail.py:1 and 4 more
26 references to secretsin 10 files: scaffolding/jev_client.py:8 references/02-openrouter-decisions-api.md:10 scaffolding/.env.example:1 and 7 more
No requests to vote in Hot

Show all 115 signals by file

`PROVENANCE.md`

Network accessline 15

- TypeSafe documentation: https://docs.typesafe.ai/

Network accessline 16

- TypeSafe HTTP API: https://docs.typesafe.ai/api

Network accessline 17

- TypeSafe Score reference: https://docs.typesafe.ai/primitives/score

Network accessline 18

- TypeSafe's official agent skill: https://github.com/typesafe-ai/skills

Network accessline 19

- TypeSafe's JEV announcement:   https://typesafe.ai/blog/introducing-system-one-models-and-jev - OpenRouter's JEV model page: https://openrouter.ai/typesafe/jev-1.13

Network accessline 20

https://typesafe.ai/blog/introducing-system-one-models-and-jev

Network accessline 21

- OpenRouter's JEV model page: https://openrouter.ai/typesafe/jev-1.13

`README.md`

Network accessline 3

An independent agent skill for designing, implementing, testing, and tuning a bounded [JEV](https://docs.typesafe.ai/) decision layer.

Network accessline 4

bounded [JEV](https://docs.typesafe.ai/) decision layer.

Network accessline 11

This repository is independently produced. It is not an official TypeSafe or OpenRouter product. TypeSafe publishes its own MIT-licensed [official agent skill](https://github.com/typesafe-ai/skills).

Network accessline 13

[official agent skill](https://github.com/typesafe-ai/skills).

Network accessline 23

mkdir -p ~/.codex/skills git clone https://github.com/grandamenium/jev-anything.git \

Network accessline 24

git clone https://github.com/grandamenium/jev-anything.git \

Network accessline 31

mkdir -p ~/.claude/skills git clone https://github.com/grandamenium/jev-anything.git \

Network accessline 32

git clone https://github.com/grandamenium/jev-anything.git \

Network accessline 53

1. Create a key at <https://console.typesafe.ai/keys>.

Access to secretsline 57
```
[Credential-related source omitted]
```

Network accessline 60

3. Follow the current first-party    [HTTP API](https://docs.typesafe.ai/api) or

Network accessline 61

[HTTP API](https://docs.typesafe.ai/api) or

Network accessline 62

[Python SDK](https://docs.typesafe.ai/sdk/python) documentation.

Network accessline 71

1. Create a key at <https://openrouter.ai/keys>.

Access to secretsline 75
```
[Credential-related source omitted]
```

Network accessline 85

Check the live [JEV model page](https://openrouter.ai/typesafe/jev-1.13) before

`SKILL.md`

Access to secretsline 134
```
[Credential-related source omitted]
```
Access to secretsline 136
```
[Credential-related source omitted]
```

`START-HERE.md`

Network accessline 10

an official TypeSafe or OpenRouter product, and neither company has endorsed it. TypeSafe also publishes an official, MIT-licensed agent skill at <https://github.com/typesafe-ai/skills>; use that official skill when you want the

Network accessline 11

TypeSafe also publishes an official, MIT-licensed agent skill at <https://github.com/typesafe-ai/skills>; use that official skill when you want the vendor-maintained, live-docs-first path.

Network accessline 12

<https://github.com/typesafe-ai/skills>; use that official skill when you want the

Network accessline 31

mkdir -p ~/.codex/skills git clone https://github.com/grandamenium/jev-anything.git \

Network accessline 32

git clone https://github.com/grandamenium/jev-anything.git \

Network accessline 39

mkdir -p ~/.claude/skills git clone https://github.com/grandamenium/jev-anything.git \

Network accessline 40

git clone https://github.com/grandamenium/jev-anything.git \

Network accessline 83

TypeSafe's direct API is currently available. Create a key at <https://console.typesafe.ai/keys>, set `TYPESAFE_API_KEY`, and use the current

Network accessline 84
```
[Credential-related source omitted]
```
Access to secretsline 84
```
[Credential-related source omitted]
```

Network accessline 85

first-party [HTTP API](https://docs.typesafe.ai/api) or

Network accessline 86

[SDK documentation](https://docs.typesafe.ai/sdk/python). The official API uses

Network accessline 87

`POST https://api.typesafe.ai/v1/systemone` and the current model alias

Network accessline 90

The dependency-free clients included in this starter kit instead target OpenRouter. For that path, create a key at <https://openrouter.ai/keys> and set:

Network accessline 91

OpenRouter. For that path, create a key at <https://openrouter.ai/keys> and set:

Access to secretsline 94
```
[Credential-related source omitted]
```

Network accessline 97

Never paste a real key into a prompt, source file, screenshot, or recording. Check the live model page at <https://openrouter.ai/typesafe/jev-1.13> immediately

Network accessline 98

Check the live model page at <https://openrouter.ai/typesafe/jev-1.13> immediately

`references/01-what-jev-is.md`

Network accessline 64

- TypeSafe official: https://typesafe.ai/blog/introducing-system-one-models-and-jev

Network accessline 65

- Current TypeSafe docs: https://docs.typesafe.ai/

Network accessline 66

- Official TypeSafe agent skill (MIT): https://github.com/typesafe-ai/skills

`references/02-openrouter-decisions-api.md`

Network accessline 9

- Create a key: https://console.typesafe.ai/keys

Network accessline 10
```
[Credential-related source omitted]
```
Access to secretsline 10
```
[Credential-related source omitted]
```

Network accessline 11

- Endpoint: `POST https://api.typesafe.ai/v1/systemone`

Network accessline 12

- Current model alias: `jev-latest` - HTTP API: https://docs.typesafe.ai/api - Python SDK: https://docs.typesafe.ai/sdk/python

Network accessline 13

- HTTP API: https://docs.typesafe.ai/api

Network accessline 14

- Python SDK: https://docs.typesafe.ai/sdk/python

Network accessline 15

- JavaScript SDK: https://docs.typesafe.ai/sdk/javascript

Network accessline 16

- Official agent skill: https://github.com/typesafe-ai/skills (MIT licensed)

Network accessline 24
```
[Credential-related source omitted]
```
Access to secretsline 24
```
[Credential-related source omitted]
```
Access to secretsline 25
```
[Credential-related source omitted]
```

Network accessline 26

- Model slug: `typesafe/jev-1.13` on the raw API; `jev-1.13` when using the SDK   with the OpenRouter base URL. The live model page is   https://openrouter.ai/typesafe/jev-1.13 (check it for the current version and

Network accessline 27

with the OpenRouter base URL. The live model page is   https://openrouter.ai/typesafe/jev-1.13 (check it for the current version and   price).

Network accessline 28

https://openrouter.ai/typesafe/jev-1.13 (check it for the current version and

Network accessline 40
```
[Credential-related source omitted]
```
Network accessline 41
```
[Credential-related source omitted]
```
Access to secretsline 41
```
[Credential-related source omitted]
```
Network accessline 42
```
base_url="https://openrouter.ai/api",
```

Network accessline 103

ENDPOINT - LIVE-VERIFIED 2026-09-22: `POST https://openrouter.ai/api/alpha/decisions`

Network accessline 104

WORKS on OpenRouter (tested against a real key; request and response shapes below confirmed live). An alternate path `https://openrouter.ai/api/v1/systemone` also appears in some docs; `alpha/decisions` is the confirmed one. The scaffolding

Network accessline 105

confirmed live). An alternate path `https://openrouter.ai/api/v1/systemone` also

`scaffolding/.env.example`

Network accessline 1
```
[Credential-related source omitted]
```
Access to secretsline 1
```
[Credential-related source omitted]
```
Access to secretsline 2
```
[Credential-related source omitted]
```

Network accessline 4

# For TypeSafe's official SDK/direct API instead: https://console.typesafe.ai/keys

Access to secretsline 5
```
[Credential-related source omitted]
```

`scaffolding/evaluate.py`

Executable scriptline 1
```
Executable file
```

`scaffolding/examples/email_triage.py`

Executable scriptline 1
```
Executable file
```
Access to secretsline 3
```
[Credential-related source omitted]
```

`scaffolding/examples/guardrail.py`

Executable scriptline 1
```
Executable file
```
Access to secretsline 3
```
[Credential-related source omitted]
```

`scaffolding/examples/pr_risk_score.py`

Executable scriptline 1
```
Executable file
```
Access to secretsline 3
```
[Credential-related source omitted]
```

`scaffolding/jev_client.py`

Executable scriptline 1
```
Executable file
```
Network accessline 8
```
[Credential-related source omitted]
```
Access to secretsline 8
```
[Credential-related source omitted]
```
Network accessline 9
```
https://openrouter.ai/keys).
```

Network accessline 12

below as ENDPOINT so it is a one-line change. If a call 404s, switch it to the other documented path, or use the official `typesafe_sdk` instead (which handles the path for you). Verify against https://openrouter.ai/typesafe/jev-1.13 .

Network accessline 13

other documented path, or use the official `typesafe_sdk` instead (which handles the path for you). Verify against https://openrouter.ai/typesafe/jev-1.13 . """

Network accessline 14

the path for you). Verify against https://openrouter.ai/typesafe/jev-1.13 .

Network accessline 24

ENDPOINT = "https://openrouter.ai/api/alpha/decisions"

Network accessline 25

# ALT_ENDPOINT = "https://openrouter.ai/api/v1/systemone"

Access to secretsline 55
```
[Credential-related source omitted]
```
Access to secretsline 60
```
[Credential-related source omitted]
```
Access to secretsline 61
```
[Credential-related source omitted]
```
Access to secretsline 62
```
[Credential-related source omitted]
```

Network accessline 64

body = json.dumps({"model": MODEL, "state": state, "questions": questions}).encode()     req = urllib.request.Request(

Network accessline 65
```
req = urllib.request.Request(
```
Access to secretsline 69
```
[Credential-related source omitted]
```

Network accessline 73

)     try:         with urllib.request.urlopen(req, timeout=timeout) as resp:

Network accessline 74

try:         with urllib.request.urlopen(req, timeout=timeout) as resp:             return json.loads(resp.read().decode())

Network accessline 75

with urllib.request.urlopen(req, timeout=timeout) as resp:

Access to secretsline 103
```
[Credential-related source omitted]
```

`scaffolding/jev_client.ts`

Executable scriptline 1
```
Executable file
```

Network accessline 6

* confidence. See ../references/02-openrouter-decisions-api.md.  *  * Auth: set OPENROUTER_API_KEY (get a key at https://openrouter.ai/keys).

Network accessline 7

*  * Auth: set OPENROUTER_API_KEY (get a key at https://openrouter.ai/keys).  *

Network accessline 8
```
[Credential-related source omitted]
```
Access to secretsline 8
```
[Credential-related source omitted]
```

Network accessline 11

* below. If a call 404s, switch to ALT_ENDPOINT or use the official  * @typesafe-ai/sdk (which handles the path). Verify at  * https://openrouter.ai/typesafe/jev-1.13

Network accessline 12

* @typesafe-ai/sdk (which handles the path). Verify at  * https://openrouter.ai/typesafe/jev-1.13  */

Network accessline 13

* https://openrouter.ai/typesafe/jev-1.13

Network accessline 16

const MODEL = "typesafe/jev-1.13"; const ENDPOINT = "https://openrouter.ai/api/alpha/decisions";

Network accessline 17

const ENDPOINT = "https://openrouter.ai/api/alpha/decisions";

Network accessline 18

// const ALT_ENDPOINT = "https://openrouter.ai/api/v1/systemone";

Access to secretsline 51
```
[Credential-related source omitted]
```
Access to secretsline 52
```
[Credential-related source omitted]
```

Network accessline 54

const res = await fetch(opts.endpoint ?? ENDPOINT, {

`scaffolding/make_rating_sheet.py`

Executable scriptline 1
```
Executable file
```

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 110 facts

Network access in prose of documentationPROVENANCE.md:15Low confidence
Network access in prose of documentationPROVENANCE.md:16Low confidence
Network access in prose of documentationPROVENANCE.md:17Low confidence
Network access in prose of documentationPROVENANCE.md:18Low confidence
Network access in prose of documentationPROVENANCE.md:19Low confidence
Network access in prose of documentationPROVENANCE.md:20Low confidence
Network access in prose of documentationPROVENANCE.md:21Low confidence
Network access in prose of documentationREADME.md:3Low confidence
Network access in prose of documentationREADME.md:4Low confidence
Network access in prose of documentationREADME.md:11Low confidence
Network access in prose of documentationREADME.md:13Low confidence
Network access in code of documentationREADME.md:23Low confidence
Network access in code of documentationREADME.md:24Low confidence
Network access in code of documentationREADME.md:31Low confidence
Network access in code of documentationREADME.md:32Low confidence
Network access in prose of documentationREADME.md:53Low confidence
Access to secrets in code of documentation: a variable, placeholder or call, not a stored valueREADME.md:57Low confidence
Network access in prose of documentationREADME.md:60Low confidence
Network access in prose of documentationREADME.md:61Low confidence
Network access in prose of documentationREADME.md:62Low confidence
Network access in prose of documentationREADME.md:71Low confidence
Access to secrets in code of documentation: a variable, placeholder or call, not a stored valueREADME.md:75Low confidence
Network access in prose of documentationREADME.md:85Low confidence
Access to secrets in prose of the SKILL.mdSKILL.md:134Low confidence
Access to secrets in prose of the SKILL.mdSKILL.md:136Low confidence
Network access in prose of documentationSTART-HERE.md:10Low confidence
Network access in prose of documentationSTART-HERE.md:11Low confidence
Network access in prose of documentationSTART-HERE.md:12Low confidence
Network access in code of documentationSTART-HERE.md:31Low confidence
Network access in code of documentationSTART-HERE.md:32Low confidence
Network access in code of documentationSTART-HERE.md:39Low confidence
Network access in code of documentationSTART-HERE.md:40Low confidence
Network access in prose of documentationSTART-HERE.md:83Low confidence
Network access in prose of documentationSTART-HERE.md:84Low confidence
Access to secrets in prose of documentationSTART-HERE.md:84Low confidence
Network access in prose of documentationSTART-HERE.md:85Low confidence
Network access in prose of documentationSTART-HERE.md:86Low confidence
Network access in prose of documentationSTART-HERE.md:87Low confidence
Network access in prose of documentationSTART-HERE.md:90Low confidence
Network access in prose of documentationSTART-HERE.md:91Low confidence
Access to secrets in code of documentation: a variable, placeholder or call, not a stored valueSTART-HERE.md:94Low confidence
Network access in prose of documentationSTART-HERE.md:97Low confidence
Network access in prose of documentationSTART-HERE.md:98Low confidence
Network access in prose of documentationreferences/01-what-jev-is.md:64Low confidence
Network access in prose of documentationreferences/01-what-jev-is.md:65Low confidence
Network access in prose of documentationreferences/01-what-jev-is.md:66Low confidence
Network access in prose of documentationreferences/02-openrouter-decisions-api.md:9Low confidence
Network access in prose of documentationreferences/02-openrouter-decisions-api.md:10Low confidence
Access to secrets in prose of documentationreferences/02-openrouter-decisions-api.md:10Low confidence
Network access in prose of documentationreferences/02-openrouter-decisions-api.md:11Low confidence

and 60 more

Works with

Agent compatibility, from the files in this repository
Agent	Status	Evidence	Install to
Claude Code	Compatible	Standard SKILL.md SKILL.md	`.claude/skills/<skill-name>/`
Codex	Compatible	Standard SKILL.md SKILL.md	`.agents/skills/<skill-name>/`
Cursor	Compatible	Standard SKILL.md SKILL.md	`.cursor/skills/<skill-name>/`
Gemini CLI	Compatible	Standard SKILL.md SKILL.md	`.gemini/skills/<skill-name>/`
GitHub Copilot	Compatible	Standard SKILL.md SKILL.md	`.github/skills/<skill-name>/`
OpenCode	Compatible	Standard SKILL.md SKILL.md	`.opencode/skills/<skill-name>/`

Native The repository ships a manifest, folder or frontmatter field for this agent.
Compatible A standard SKILL.md that this agent can read.
Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

grandamenium/jev-anything

History

SKILL.md

Share this page

Heat

Stars over time

Individual skills in this repository

How it works

jev-anything

Frontmatter

SKILL.md

Reference documents

The playbook

Scripts executed separately

Files

Skills included

Repository facts

Before you install

PROVENANCE.md

README.md

SKILL.md

START-HERE.md

references/01-what-jev-is.md

references/02-openrouter-decisions-api.md

scaffolding/.env.example

scaffolding/evaluate.py

scaffolding/examples/email_triage.py

scaffolding/examples/guardrail.py

scaffolding/examples/pr_risk_score.py

scaffolding/jev_client.py

scaffolding/jev_client.ts

scaffolding/make_rating_sheet.py

How the signals fit together

Works with

You might also use

0xNyk/council-of-high-intelligence

backant-io/jevelry

op7418/guizang-social-card-skill

isjiamu/gzh-design-skill

oil-oil/oil-motion

Astro-Han/karpathy-llm-wiki

`SKILL.md`

`PROVENANCE.md`

`README.md`

`SKILL.md`

`START-HERE.md`

`references/01-what-jev-is.md`

`references/02-openrouter-decisions-api.md`

`scaffolding/.env.example`

`scaffolding/evaluate.py`

`scaffolding/examples/email_triage.py`

`scaffolding/examples/guardrail.py`

`scaffolding/examples/pr_risk_score.py`

`scaffolding/jev_client.py`

`scaffolding/jev_client.ts`

`scaffolding/make_rating_sheet.py`