pre-compact SKILL.md skillA

pre-compact from tenequm/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add tenequm/skills/pre-compact@v0.1.5

Pins v0.1.5 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
tenequm/skills
Path
skills/pre-compact/SKILL.md
Versions recorded
6
Latest version
v0.1.5, committed Nov 5, 2026
First version recorded
Aug 21, 2026
Size
2,635 bytes
Repository stars
39
License
MIT

Prepare the session for context compaction - write a handoff file a fresh session can continue from, propose updates to the project's durable docs, apply them on approval or with `auto`. Use before compacting or clearing context, or on "pre-compact".

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

I will compact this context soon. The summary can be wrong. Files are the
source of truth. Move everything a fresh session needs from this conversation
into files. Mode: $ARGUMENTS. `auto` or `a` means: apply all proposed updates
without asking.

Write `.agents/compact-handoff/YYMM-DD-HHMM-<short-slug>.md`. Start with the
line `# Handoff <date> <time> <repo>@<branch>`. Then write these sections:

- Position: what we are doing, why, and where we stopped.
- Next steps: in order, with the paths, commands and identifiers needed to run them.
- Decisions: each decision made here, with its reason.
- Findings: what we learned works or fails, verbatim.
- Open questions: numbered, each with your recommended answer.
- Undone instructions: what I asked for that is not done.
- References: files, links, related docs.

Copy numbers, commands and paths exactly. Do not paraphrase them. Never write
secrets, tokens, passwords or API keys into the handoff. Write where they
live instead, for example the env var name or the vault item. Record only
decisions that were made. Keep open questions open.

Then check the docs this project uses to track work: plans, journals, status
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add tenequm/skills/pre-compact@sha256:900ad66ea0de9ea9

The line at the top of this page pins the label v0.1.5, 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_jlrs6riftnumoxhi.svg)](https://markdownregistry.com/a/art_jlrs6riftnumoxhi)

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

Versions

The registry has recorded 6 versions of this file, between Aug 21, 2026 and Nov 5, 2026, about one every 15 days.

versioncommittedcommitsizeaudit
v0.1.5 latest2026-11-05 cb14e29 2,635 BA view · diff
v0.1.42026-09-09 7581ac6 2,635 BA view · diff
v0.1.32026-08-21 b16c242 2,666 BA view · diff
v0.1.22026-08-21 dcdbefb 2,558 BA view · diff
v0.1.12026-08-21 e79db33 2,410 BA view · diff
v0.1.02026-08-21 4418c65 1,768 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 (2635 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

tenequm/skills · 39 stars · license MIT · pushed 2026-11-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_jlrs6riftnumoxhi
GET https://markdownregistry.com/api/v1/resolve?ref=tenequm/skills/pre-compact
GET https://markdownregistry.com/api/v1/blob/900ad66ea0de9ea9ff1f0e16f365bbfb36b519c26c2925d379be7fc6c5688b3d

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 tenequm/skills

AGENTS.md AGENTS.md file
tenequm/skills · AGENTS.md
git:20261105.16996da · audit A · 39 stars
audio-quality-check SKILL.md skill
tenequm/skills · archive/audio-quality-check/SKILL.md · Analyzes audio recording quality - echo detection, loudness, speech intelligibility, SNR, and spectral analysis. Use…
v0.1.4 · audit A · 39 stars
chrome-extension-wxt SKILL.md skill
tenequm/skills · archive/chrome-extension-wxt/SKILL.md · Build Chrome extensions with the WXT framework and TypeScript, React, Vue, or Svelte. Use when creating browser…
v1.1.5 · audit B · 39 stars
cloudflare-workers SKILL.md skill
tenequm/skills · archive/cloudflare-workers/SKILL.md · Rapid development with Cloudflare Workers - build and deploy serverless applications on Cloudflare's global network…
v3.1.3 · audit A · 39 stars
effect-ts SKILL.md skill
tenequm/skills · archive/effect-ts/SKILL.md · Effect-TS guide for TypeScript, v4 default with v3 support. Use when writing, debugging, or reviewing Effect code…
v0.6.5 · audit A · 39 stars
erc-8004 SKILL.md skill
tenequm/skills · archive/erc-8004/SKILL.md · Build with ERC-8004 Trustless Agents - on-chain agent identity, reputation, validation, and discovery on EVM chains…
v0.2.4 · audit A · 39 stars
foundry-solidity SKILL.md skill
tenequm/skills · archive/foundry-solidity/SKILL.md · Build and test Solidity contracts with Foundry. Use when developing Ethereum contracts, writing Forge tests, deploying…
v0.2.5 · audit A · 39 stars
gh-cli SKILL.md skill
tenequm/skills · archive/gh-cli/SKILL.md · GitHub CLI for remote repository analysis, file fetching, codebase comparison, and discovering trending code/repos. Use…
v1.4.0 · audit A · 39 stars
grafana-foundation-sdk SKILL.md skill
tenequm/skills · archive/grafana-foundation-sdk/SKILL.md · Build Grafana dashboards as code with the grafana-foundation-sdk typed builders (TypeScript or Go). Use when creating…
v0.2.4 · audit A · 39 stars
herdr-faq SKILL.md skill
tenequm/skills · archive/herdr-faq/SKILL.md · Launch and drive coding agents (codex, claude, agy) through the Herdr CLI; requires a herdr pane (HERDR_ENV=1). Use…
v0.5.0 · audit A · 39 stars
impactful-writing SKILL.md skill
tenequm/skills · archive/impactful-writing/SKILL.md · Write clear, emotionally resonant, and well-structured content that readers remember and act upon. Use when writing or…
v0.1.4 · audit A · 39 stars
mpp SKILL.md skill
tenequm/skills · archive/mpp/SKILL.md · Build with MPP (Machine Payments Protocol), open machine-to-machine payments over HTTP 402. Use for paid APIs…
v0.10.2 · audit A · 39 stars

Every file in tenequm/skills

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