AGENTS.md@claude/dev-mods/tool-historyA

AGENTS.md@claude/dev-mods/tool-history from ronnasayd/aipp is an AGENTS.md file: the standing instructions coding agents read in that repo.

Install it, pinned
mdr add ronnasayd/aipp/claude/dev-mods/tool-history/AGENTS.md@git:20261105.4ba4217

Pins git:20261105.4ba4217 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
AGENTS.md file
Repository
ronnasayd/aipp
Path
claude/dev-mods/tool-history/AGENTS.md
Versions recorded
5
Latest version
git:20261105.4ba4217, committed Nov 5, 2026
First version recorded
Oct 29, 2026
Size
2,806 bytes
Repository stars
3
License
none declared

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

# tool-history

## Card spacing

- Cards in the pane (tool calls and agent messages) sit flush: the `list` Box
  in `hooks/register.tsx` uses `gap={0}`. No blank line between cards — the
  round border already separates them.
- Do not add `gap`, `marginY`, `marginTop` or `marginBottom` to the `list` Box
  or to individual cards. `tests/collapse.test.tsx` asserts `gap` is `0`.
- Why: when cards were grouped per agent, `gap={1}` only separated groups.
  After the groups were flattened (each card names its agent), the same
  `gap={1}` landed between every card and the pane got sparse.

## Border colors

- Yellow border = subagent, and only in the messages tab (agent message cards).
- Tool call cards (Bash, Read, etc.) never use yellow, even when a subagent
  made the call: `danger` on error, `subtle` when done, `claude` while running.
  `tests/subagent-border.test.tsx` asserts this.

## Agent tool calls in the messages tab

- Each `Agent` tool call also adds a `kind: "agent"` card to the messages tab
  (key `agent-call-<tool_use_id>`): `subagent_type`, `description` and the
  full `prompt`. Border follows the caller (yellow only if a subagent spawned
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add ronnasayd/aipp/claude/dev-mods/tool-history/AGENTS.md@sha256:3e3b3c258bf78630

The line at the top of this page pins the label git:20261105.4ba4217, 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_tp6s23pxkutz3wah.svg)](https://markdownregistry.com/a/art_tp6s23pxkutz3wah)

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 ronnasayd/aipp/claude/dev-mods/tool-history/AGENTS.md 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 AGENTS.md from somewhere else? Ask it: where did my AGENTS.md 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 5 versions of this file, between Oct 29, 2026 and Nov 5, 2026, about one every 2 days.

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

versioncommittedcommitsizeaudit
git:20261105.4ba4217 latest2026-11-05 4ba4217 2,806 BA view · diff
git:20261104.2e803762026-11-04 2e80376 2,805 BA view · diff
git:20261103.224a30c2026-11-03 224a30c 2,111 BA view · diff
git:20261029.fde17f92026-10-29 fde17f9 1,605 BA view · diff
git:20261029.2e3b9b12026-10-29 2e3b9b1 1,225 BA view
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  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (2806 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

ronnasayd/aipp · 3 stars · license none declared · pushed 2026-11-18 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_tp6s23pxkutz3wah
GET https://markdownregistry.com/api/v1/resolve?ref=ronnasayd/aipp/claude/dev-mods/tool-history/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/3e3b3c258bf78630cbe73aec6a067695ce50e85dea07240daaaeb29fd8f78db1

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: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.

More from ronnasayd/aipp

AGENTS.md AGENTS.md file
ronnasayd/aipp · AGENTS.md
git:20261105.0bfe3dc · audit A · 3 stars
CLAUDE.md CLAUDE.md file
ronnasayd/aipp · CLAUDE.md
git:20260919.ef9a503 · audit A · 3 stars
discovery-process SKILL.md skill
ronnasayd/aipp · skills/Product-Manager-Skills/discovery-process/SKILL.md · Run a full discovery cycle from problem hypothesis to validated solution. Use when a team needs a structured path…
git:20261109.95e8e67 · audit A · 3 stars
prd-development SKILL.md skill
ronnasayd/aipp · skills/Product-Manager-Skills/prd-development/SKILL.md · Build a structured PRD that connects problem, users, solution, and success criteria. Use when turning discovery notes…
git:20261109.95e8e67 · audit A · 3 stars
user-story-mapping SKILL.md skill
ronnasayd/aipp · skills/Product-Manager-Skills/user-story-mapping/SKILL.md · Create a user story map that lays out activities, steps, tasks, and release slices. Use when planning a workflow…
git:20261109.95e8e67 · audit A · 3 stars
user-story-splitting SKILL.md skill
ronnasayd/aipp · skills/Product-Manager-Skills/user-story-splitting/SKILL.md · Break a large story or epic into smaller deliverable stories using proven split patterns. Use when backlog items are…
git:20261109.95e8e67 · audit A · 3 stars
user-story SKILL.md skill
ronnasayd/aipp · skills/Product-Manager-Skills/user-story/SKILL.md · Create user stories with Mike Cohn format and Gherkin acceptance criteria. Use when turning user needs into…
git:20261109.95e8e67 · audit A · 3 stars
skill-inspector SKILL.md skill
ronnasayd/aipp · skills/SkillSpector/skill-inspector/SKILL.md · Review AI agent skills before installation using NVIDIA SkillSpector and source-aware semantic review. Use when asked…
git:20261027.315f0f5 · audit A · 3 stars
adversarial-dev SKILL.md skill
ronnasayd/aipp · skills/adversarial-dev/SKILL.md · Orchestrates a code task through two separate agents in an adversarial loop — an executor that implements and a strict…
v1.0.0 · audit A · 3 stars
agent-creator SKILL.md skill
ronnasayd/aipp · skills/agent-creator/SKILL.md · Create new specialist agents, modify and improve existing agents, and validate agent behavior. Use when users want to…
v1.0.0 · audit A · 3 stars
skill-judge SKILL.md skill
ronnasayd/aipp · skills/agent-toolkit/skill-judge/SKILL.md · Evaluate Agent Skill design quality against official specifications and best practices. Use when reviewing, auditing…
git:20260926.0cb2534 · audit A · 3 stars
aipp-guide SKILL.md skill
ronnasayd/aipp · skills/aipp-guide/SKILL.md · Explain how to use the AIPP toolkit (this repo, also called aipp): installing it, linking it into a project, enabling…
v1.0.0 · audit A · 3 stars

Every file in ronnasayd/aipp

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