du-dum SKILL.md skillA

du-dum from pjt222/agent-almanac is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add pjt222/agent-almanac/du-dum@v1.0

Pins v1.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
pjt222/agent-almanac
Path
i18n/caveman-lite/skills/du-dum/SKILL.md
Versions recorded
5
Latest version
v1.0, committed Aug 17, 2026
First version recorded
Apr 19, 2026
Size
13,429 bytes
Repository stars
43
License
MIT

Separate expensive observation from cheap decision-making in autonomous agent loops using a two-clock architecture. A fast clock accumulates data into a digest file; a slow clock reads the digest and acts only when something is pending. Idle cycles cost nothing because the action clock returns immediately after reading an empty digest. Use when building autonomous agents that must observe continuously but can only afford to act occasionally, when API or LLM costs dominate and most cycles have…

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

# Du-Dum: Batch-Then-Act Pattern

Separate observation from action using two clocks running at different frequencies. The fast clock (analysis) collects data cheaply and writes a compact digest. The slow clock (action) reads the digest and decides whether to act. If the digest says nothing pending, the action clock exits immediately -- zero cost for idle cycles.

The name comes from the heartbeat rhythm: du-dum, du-dum. The first beat (du) observes; the second beat (dum) acts. Most of the time, only the first beat fires.

## When to Use

- Building autonomous agents that run on a budget and must observe more often than they act
- An existing heartbeat loop calls the LLM every tick, even when nothing has changed
- Observation is cheap (API reads, file parsing, log scanning) but action is expensive (LLM calls, write operations, notifications)
- You need decoupled failure: if observation fails, the last good digest should still be valid for the action clock
- Designing cron-based agent architectures where analysis and action run as separate jobs

## Inputs

- **Required**: List of data sources the fast clock should observe (APIs, files, logs, feeds)
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add pjt222/agent-almanac/du-dum@sha256:c25f21e71462fb5f

The line at the top of this page pins the label v1.0, 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_w2uhbf5wqf3qwxet.svg)](https://markdownregistry.com/a/art_w2uhbf5wqf3qwxet)

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

Versions

The registry has recorded 5 versions of this file, between Apr 19, 2026 and Aug 17, 2026, about one every 30 days.

versioncommittedcommitsizeaudit
v1.0 latest2026-08-17 a784899 13,429 BA view · diff
v1.02026-06-05 33b561c 13,400 BA view · diff
v1.02026-06-05 75ded7a 13,384 BA view · diff
v1.02026-04-24 0b91b04 13,477 BA view · diff
v1.02026-04-19 e334ebd 13,535 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 (13429 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

pjt222/agent-almanac · 43 stars · license MIT · pushed 2026-11-06 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_w2uhbf5wqf3qwxet
GET https://markdownregistry.com/api/v1/resolve?ref=pjt222/agent-almanac/du-dum
GET https://markdownregistry.com/api/v1/blob/c25f21e71462fb5f6c4e8bdc42156edaaafda659d6dcc6cfea209c1a9004a047

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 pjt222/agent-almanac

CLAUDE.md CLAUDE.md file
pjt222/agent-almanac · CLAUDE.md
git:20261105.d2f5ad6 · audit A · 43 stars
adapt-architecture SKILL.md skill
pjt222/agent-almanac · i18n/caveman-lite/skills/adapt-architecture/SKILL.md · Execute structural metamorphosis using strangler fig migration, chrysalis phases, and interface preservation. Covers…
v1.0 · audit A · 43 stars
adaptic SKILL.md skill
pjt222/agent-almanac · i18n/caveman-lite/skills/adaptic/SKILL.md · Master skill composing the 5-step synoptic cycle for panoramic synthesis across multiple domains. Orchestrates…
v1.0 · audit A · 43 stars
add-puzzle-type SKILL.md skill
pjt222/agent-almanac · i18n/caveman-lite/skills/add-puzzle-type/SKILL.md · Scaffold a new puzzle type across all 10+ pipeline integration points in jigsawR. Creates the core puzzle module, wires…
v1.0 · audit A · 43 stars
add-rcpp-integration SKILL.md skill
pjt222/agent-almanac · i18n/caveman-lite/skills/add-rcpp-integration/SKILL.md · Add Rcpp or RcppArmadillo integration to an R package for high-performance C++ code. Covers setup, writing C++…
v1.0 · audit A · 43 stars
aikido SKILL.md skill
pjt222/agent-almanac · i18n/caveman-lite/skills/aikido/SKILL.md · Practice aikido as a defensive martial art emphasizing harmony, redirection, and controlled resolution. Covers…
v1.0 · audit A · 43 stars
analyze-codebase-for-mcp SKILL.md skill
pjt222/agent-almanac · i18n/caveman-lite/skills/analyze-codebase-for-mcp/SKILL.md · Analyze an arbitrary codebase to identify functions, APIs, and data sources suitable for exposure as MCP tools…
v1.0 · audit A · 43 stars
analyze-codebase-workflow SKILL.md skill
pjt222/agent-almanac · i18n/caveman-lite/skills/analyze-codebase-workflow/SKILL.md · Analyze an arbitrary codebase to auto-detect workflows, data pipelines, and file dependencies using putior's put_auto()…
v1.0 · audit A · 43 stars
analyze-diffusion-dynamics SKILL.md skill
pjt222/agent-almanac · i18n/caveman-lite/skills/analyze-diffusion-dynamics/SKILL.md · Analyze the dynamics of diffusion processes using stochastic differential equations, Fokker-Planck equations…
v1.0 · audit A · 43 stars
analyze-generative-diffusion-model SKILL.md skill
pjt222/agent-almanac · i18n/caveman-lite/skills/analyze-generative-diffusion-model/SKILL.md · Analyze pre-trained generative diffusion models (Stable Diffusion, DALL-E, Flux) by computing quality metrics (FID, IS…
v1.0 · audit A · 43 stars
analyze-kernel-bottleneck SKILL.md skill
pjt222/agent-almanac · i18n/caveman-lite/skills/analyze-kernel-bottleneck/SKILL.md · Systematically identify whether a GPU kernel is compute-bound, memory-bound, or latency-bound using roofline analysis…
v1.0 · audit A · 43 stars
analyze-magnetic-field SKILL.md skill
pjt222/agent-almanac · i18n/caveman-lite/skills/analyze-magnetic-field/SKILL.md · Calculate and visualize magnetic fields produced by current distributions using the Biot-Savart law, Ampere's law, and…
v1.0 · audit A · 43 stars

Every file in pjt222/agent-almanac

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