AGENTS.md@snippets/systems-thinkingA

AGENTS.md@snippets/systems-thinking from parcha-ai/parcha-skills is an AGENTS.md file: the standing instructions coding agents read in that repo.

Install it, pinned
mdr add parcha-ai/parcha-skills/snippets/systems-thinking/AGENTS.md@git:20260725.7c99829

Pins git:20260725.7c99829 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
AGENTS.md file
Repository
parcha-ai/parcha-skills
Path
snippets/systems-thinking/AGENTS.md
Versions recorded
1
Latest version
git:20260725.7c99829, committed Jul 25, 2026
Size
1,205 bytes
Repository stars
123
License
MIT

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

<!-- systems-thinking:start -->
## Systems Thinking

- Improve the whole, not an isolated part. Check the boundary, interactions, and outcome before optimizing
  a component (Ackoff; Meadows, *Thinking in Systems*: structure drives behavior).
- Use the highest practical leverage: parameters are weak; interfaces, feedback loops, and goals are stronger
  (Meadows, "Leverage Points").
- Label a fix as symptomatic or fundamental. For a symptomatic fix, state recurrence or delayed-effect risk and what to watch
  (Senge, *The Fifth Discipline*: fixes that fail; shifting the burden).
- Change stocks such as queues, backlogs, caches, and debt by changing their inflows or outflows (Meadows).
- Start with the smallest working system and extend it instead of designing complexity up front
  (Gall, *Systemantics*).
- Treat unusual structure as evidence. Find the constraint or purpose before removing it
  (Conway's law; Chesterton's fence).
- Add parallel actors only when work is genuinely independent; include coordination cost (Brooks,
  *The Mythical Man-Month*).
- When a change is bounded and local, act. State a systemic concern in one sentence, then finish the work.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add parcha-ai/parcha-skills/snippets/systems-thinking/AGENTS.md@sha256:81ec6241d11d1b58

The line at the top of this page pins the label git:20260725.7c99829, 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_jdzuwdzusxtrb5mx.svg)](https://markdownregistry.com/a/art_jdzuwdzusxtrb5mx)

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

Versions

The registry has recorded 1 version of this file, committed on Jul 25, 2026.

versioncommittedcommitsizeaudit
git:20260725.7c99829 latest2026-07-25 7c99829 1,205 BA view

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 (1205 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

parcha-ai/parcha-skills · 123 stars · license MIT · pushed 2026-10-22 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_jdzuwdzusxtrb5mx
GET https://markdownregistry.com/api/v1/resolve?ref=parcha-ai/parcha-skills/snippets/systems-thinking/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/81ec6241d11d1b5807fe62835d0be22c9ad60f09074ebce4afccdab49c6ae452

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 parcha-ai/parcha-skills

autoqa SKILL.md skill
parcha-ai/parcha-skills · autoqa/skills/autoqa/SKILL.md · Self-QA a repo's running application end-to-end — discover how it runs, build a feature×modality test plan, execute it…
git:20260927.0a701f0 · audit A · 123 stars
blast-radius SKILL.md skill
parcha-ai/parcha-skills · blast-radius/skills/blast-radius/SKILL.md · Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe…
git:20260915.b0f7211 · audit A · 123 stars
cascade SKILL.md skill
parcha-ai/parcha-skills · cascade/skills/cascade/SKILL.md · Carry large projects through verifiable tasks, parallel work, and durable progress. Use when asked for Cascade, work in…
git:20260905.989295e · audit A · 123 stars
desloppify SKILL.md skill
parcha-ai/parcha-skills · desloppify/skills/desloppify/SKILL.md · Systematically diagnose and improve whole-codebase maintainability with the official Desloppify engine, combining…
git:20260713.08c027b · audit A · 123 stars
hands-free SKILL.md skill
parcha-ai/parcha-skills · hands-free/skills/hands-free/SKILL.md · Phone-call bridge for coding agents — when the user is away from the keyboard, the agent calls them (as Unc). Use when…
git:20260713.33e8e1d · audit A · 123 stars
parable SKILL.md skill
parcha-ai/parcha-skills · parable/skills/parable/SKILL.md · Install, onboard, and run multi-model coding orchestration or solo single-model mode. Invoke when the user says install…
git:20260830.7e18cc6 · audit A · 123 stars
precap SKILL.md skill
parcha-ai/parcha-skills · precap/skills/precap/SKILL.md · Write a precap — the recap of a task as if it were already finished — before or during long-running work, then use it…
git:20260908.9532a5d · audit A · 123 stars
recall SKILL.md skill
parcha-ai/parcha-skills · recall/skills/recall/SKILL.md · Find prior Claude Code and Codex sessions with an indexed local search engine, then continue the work, repeat it with…
git:20261022.c82883b · audit A · 123 stars
recap SKILL.md skill
parcha-ai/parcha-skills · recap/skills/recap/SKILL.md · Reconstruct what a Claude Code or Codex agent actually did during one exact session, including goals, decisions…
git:20260714.1ba3ace · audit A · 123 stars
review-loop SKILL.md skill
parcha-ai/parcha-skills · review-loop/skills/review-loop/SKILL.md · Drive every reviewer thread on a GitHub pull request to zero unresolved, iterating until the exit criterion is met…
git:20261003.22b7ecf · audit A · 123 stars
AGENTS.md@snippets/control AGENTS.md file
parcha-ai/parcha-skills · snippets/control/AGENTS.md
git:20260725.7c99829 · audit A · 123 stars
AGENTS.md@snippets/effective-comms AGENTS.md file
parcha-ai/parcha-skills · snippets/effective-comms/AGENTS.md
git:20260806.e6e5531 · audit A · 123 stars

Every file in parcha-ai/parcha-skills

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