context-window-self-clearing SKILL.md skillA
context-window-self-clearing from arcanada-one/datarim is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add arcanada-one/datarim/context-window-self-clearing@git:20261004.8dfccd1Pins git:20261004.8dfccd1 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- arcanada-one/datarim
- Path
skills/context-window-self-clearing/SKILL.md- Versions recorded
- 1
- Latest version
- git:20261004.8dfccd1, committed Oct 4, 2026
- Size
- 3,662 bytes
- Repository stars
- 16
- License
- MIT
Preserve Datarim task continuity while orchestrated Claude Code or Codex sessions compact or clear context at deterministic pressure thresholds.
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
# Context-Window Self-Clearing Use this skill only for orchestrator-launched Claude Code and Codex sessions that explicitly enable context-window automation. It is default-off. ## Contract 1. Read the active task snapshot first. Bind the active task-description path, last completed snapshot stage, snapshot path, and snapshot digest into a private transaction before sending a reset instruction. 2. Pressure has TWO arms and the stricter verdict wins. **Absolute arm (primary).** Below 200000 tokens of working set is `no_op`, 200000 through 279999 is `selective_drop`, 280000 and above is `full_clear`. Ceilings are overridable per deployment via `DR_CTX_SOFT_TOKENS` and `DR_CTX_HARD_TOKENS`. **Percentage arm (retained).** Below 75 percent is `no_op`, 75 through 89 is `selective_drop`, 90 through 100 is `full_clear`. A private exact-label policy may select a mode only at or above its declared floor, never below 50. A percentage alone cannot express pressure, because it hides its denominator: 75 percent of a 200k window is 150k tokens, while 75 percent of a 1M window is 750k. Attention degrades with the LENGTH of the accumulated …
Read the whole file at its exact version.
How to install
mdr add arcanada-one/datarim/context-window-self-clearing@sha256:8b67d202c82e730cThe line at the top of this page pins the label git:20261004.8dfccd1, 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.
[](https://markdownregistry.com/a/art_xodlvqfcj6o4hhqz)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Oct 4, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3662 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
arcanada-one/datarim · 16 stars · license MIT · pushed 2026-10-29 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_xodlvqfcj6o4hhqz GET https://markdownregistry.com/api/v1/resolve?ref=arcanada-one/datarim/context-window-self-clearing GET https://markdownregistry.com/api/v1/blob/8b67d202c82e730cc98b849dcdda8a98547b97edb6ba2b6d89a27699b9cd3459
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.