reporting-outside-effects SKILL.md skillA

reporting-outside-effects from reply-team/jason-ai is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add reply-team/jason-ai/reporting-outside-effects@git:20260921.0b08fba

Pins git:20260921.0b08fba in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
reply-team/jason-ai
Path
skills/runtime/reporting-outside-effects/SKILL.md
Versions recorded
2
Latest version
git:20260921.0b08fba, committed Sep 21, 2026
First version recorded
Sep 21, 2026
Size
8,656 bytes
Repository stars
9
License
MIT

Use when an effect on a person happened outside Jason and Jason does not know - you or somebody else sent, enrolled or replied by hand or through another tool - so that it is recorded as what was done, by whom, and when, before Jason acts on a view of the world that is wrong.

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

# Reporting effects that happened outside Jason

Jason knows about the work it performed itself. An effect produced anywhere else — a mail you sent by hand, a
person somebody enrolled through the provider's own CLI, a reply typed into a web app because the managed path
failed — leaves no trace here at all. This skill is how you tell it, and what telling it is worth.

**Status: verified** against Claude Code 2.1.278. It covers what this build records and nothing beyond it.

## Why this matters at all

Until Jason is told, its view of the world is wrong, and **it will act on that view**: a second enrolment for
somebody who has already had one, an approval question about work that is already done, a manager's review that
reads a person who has already answered as a person nobody has reached. None of that is fixed by being careful
in the conversation, because the conversation ends and the runtime goes on.

A report is **your word and nothing else**. Jason does not route it, does not verify it, does not retry it, and
**moves no work item** because of it. What it does is write down what you said, who said it and when it arrived,
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_b2spwexykcd6y2d6/09e11561cd7c8de726020ba4781787ec18c459f4f04e18cef5a7b271c5512735.json

Then /plugin install reporting-outside-effects@markdownregistry-b2spwexykcd6y2d6 in Claude Code. It installs git:20260921.0b08fba, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add reply-team/jason-ai/reporting-outside-effects@sha256:09e11561cd7c8de7

The line at the top of this page pins the label git:20260921.0b08fba, 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_b2spwexykcd6y2d6.svg)](https://markdownregistry.com/a/art_b2spwexykcd6y2d6)

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

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in reply-team/jason-ai/reporting-outside-effects since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of reporting-outside-effects from somewhere else? Ask it: where did my reporting-outside-effects come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 2 versions of this file, all committed on Sep 21, 2026.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20260921.0b08fba latest2026-09-21 0b08fba 8,656 BA view · diff
git:20260921.f0902d12026-09-21 f0902d1 7,741 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

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 (8656 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

reply-team/jason-ai · 9 stars · license MIT · pushed 2026-11-17 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_b2spwexykcd6y2d6
GET https://markdownregistry.com/api/v1/resolve?ref=reply-team/jason-ai/reporting-outside-effects
GET https://markdownregistry.com/api/v1/blob/09e11561cd7c8de726020ba4781787ec18c459f4f04e18cef5a7b271c5512735

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 reply-team/jason-ai

CLAUDE.md CLAUDE.md file
reply-team/jason-ai · CLAUDE.md
git:20261116.b93cf38 · audit A · 9 stars
approval-boundaries SKILL.md skill
reply-team/jason-ai · skills/business/approval-boundaries/SKILL.md · Where an agent must stop and ask the user before acting, how an operation's approval class is derived from its…
git:20261114.6b52d5c · audit A · 9 stars
audience-building SKILL.md skill
reply-team/jason-ai · skills/business/audience-building/SKILL.md · Turn raw prospect data into a clean, deliberately-shaped audience: decide who belongs, source or import the people…
git:20261112.f46bee4 · audit A · 9 stars
campaign-launch SKILL.md skill
reply-team/jason-ai · skills/business/campaign-launch/SKILL.md · Prepare and launch an outreach campaign with every precondition checked and the user's explicit approval of what will…
git:20261115.b0e688d · audit A · 9 stars
campaign-planning SKILL.md skill
reply-team/jason-ai · skills/business/campaign-planning/SKILL.md · Turn a vague outbound goal into an executable plan: clarify the goal until success is observable, surface the…
git:20261102.e0633ba · audit A · 9 stars
inbox-triage SKILL.md skill
reply-team/jason-ai · skills/business/inbox-triage/SKILL.md · Work the inbound replies: surface the conversations that matter first, give the user compact thread context, draft…
git:20261117.ade33bc · audit A · 9 stars
linkedin-guardrails SKILL.md skill
reply-team/jason-ai · skills/business/linkedin-guardrails/SKILL.md · Keep social accounts safe under automation: invitation pacing, messaging windows, metered allowances, daily limits and…
git:20261024.5522ec7 · audit A · 9 stars
performance-analysis SKILL.md skill
reply-team/jason-ai · skills/business/performance-analysis/SKILL.md · An honest read on outreach performance: account and per-campaign figures over a stated window, a diagnosis that…
git:20261113.e309689 · audit A · 9 stars
sdr-operations SKILL.md skill
reply-team/jason-ai · skills/business/sdr-operations/SKILL.md · The vendor-neutral contract of SDR business operations — 325 named atomic operations in 21 families, from finding and…
git:20261112.f46bee4 · audit A · 9 stars
sending-guardrails SKILL.md skill
reply-team/jason-ai · skills/business/sending-guardrails/SKILL.md · Protect sender reputation and inbox placement: domain authentication, warm-up, volume pacing, bounce interpretation and…
git:20261003.43e894c · audit A · 9 stars
approvals-and-questions SKILL.md skill
reply-team/jason-ai · skills/runtime/approvals-and-questions/SKILL.md · Use when a person asks what Jason is waiting for them to decide, or arrives because a notification said approvals or…
git:20261114.6b52d5c · audit A · 9 stars
customising-jason SKILL.md skill
reply-team/jason-ai · skills/runtime/customising-jason/SKILL.md · Use when a person asks to change how Jason itself works rather than to do campaign work - make a role write or behave…
git:20261114.6b52d5c · audit A · 9 stars

Every file in reply-team/jason-ai

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