Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not raw payloads.
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
# Guard the Context Window
The context window is finite and non-renewable within a session. Every token that enters should earn its place.
**Why:** Context overflow degrades reasoning quality, creates compression artifacts, and halts progress. Unlike compute or time, context spent inside a session cannot be reclaimed.
**Pattern:**
- **Isolate large payloads.** Route verbose outputs, screenshots, and large documents to subagents. The main context gets summaries, not raw data.
- **File-then-parse.** Never pipe a large CLI dump (trace JSON, multi-MB transcript, long log) straight into the main thread or through a pipe that the harness truncates (~30KB on Claude Code Bash). Redirect to a file first, then `jq` / read only the fields you need. Prefer extract-fields or a small structured report over fetching the full payload when the tool supports it.
- **Don't read what you won't use.** Read selectively based on relevance. If a file isn't needed for the current task, skip it.
…
The line at the top of this page pins the label git:20260923.a014aec, 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.
GET https://markdownregistry.com/api/v1/artifacts/art_igykjegluilvhrxn
GET https://markdownregistry.com/api/v1/resolve?ref=edbertchan/catstack/principle-guard-the-context-window
GET https://markdownregistry.com/api/v1/blob/5c194d0e247a4515b3e06cdb02f38658ca45dc22fa98ec5fae9637d4a43b0d17
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.
edbertchan/catstack · corpus/skills/cat-mode/SKILL.md · Edbert's personal working conventions, mined from real session history across his projects. Use when Edbert asks to…
edbertchan/catstack · corpus/skills/principle-assert-invariants-not-last-bug/SKILL.md · Apply after a bug ships past review or a passing grade/check: assert the general class of failure instead of patching…
edbertchan/catstack · corpus/skills/principle-bind-to-named-inventory/SKILL.md · Apply after an audit, scoring review, or a request for a "real classifier" / "less arbitrary weights" when existing…
edbertchan/catstack · corpus/skills/principle-build-the-lever/SKILL.md · Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or…
edbertchan/catstack · corpus/skills/principle-encode-lessons-in-structure/SKILL.md · Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction. Encode the…
edbertchan/catstack · corpus/skills/principle-experience-first/SKILL.md · Apply when product, UX, or feature-scope tradeoffs come up. Choose user delight over implementation convenience; ship…
edbertchan/catstack · corpus/skills/principle-fix-root-causes/SKILL.md · Apply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach…
edbertchan/catstack · corpus/skills/principle-flag-your-own-corrections/SKILL.md · Apply whenever you are about to admit fault in any wording — a fact, number, claim, or check you already stated turns…
edbertchan/catstack · corpus/skills/principle-generalize-from-rejection/SKILL.md · Apply when a mechanical gate — a lint, validator, blocked-command guard, or CI check — rejects your output for the same…
cursor/plugins · pstack/skills/principle-guard-the-context-window/SKILL.md · Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents…
cursor/plugins · harness/pstack/claude-code/skills/principle-guard-the-context-window/SKILL.md · Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents…
michael-denyer/pstack-claude · plugins/pstack/skills/principle-guard-the-context-window/SKILL.md · Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents…
backnotprop/pstack · skills/principle-guard-the-context-window/SKILL.md · Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents…
j-star-films-studios/vibecode-protocol-suite · assets/.agent/skills/engineering-principles/guard-the-context-window/SKILL.md · Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents…
creedants/pstack-t3 · skills/principle-guard-the-context-window/SKILL.md · Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents…
arjitj2/open-pstack · plugins/pstack/skills/principle-guard-the-context-window/SKILL.md · Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents…
painhardcore/pstack · .opencode/skills/principle-guard-the-context-window/SKILL.md · Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents…
