Use when a long session has accumulated stale or conflicting context or the user asks to refresh it. Not for remote, credential, publish, deploy, or irreversible changes.
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 engineering
## Contract
| Field | Bound contract |
|---|---|
| Trigger | Long session has accumulated stale or conflicting context, or the user asks to refresh or recheck context before continuing. |
| Authority | Reversible local: writes only an optional scratch state note; rollback is undo. No remote mutation. |
| Side effect | Optional scratch state note only; no project files touched. |
| Done | Acting context is provably current and minimal; stale items are dropped with the user informed. |
## Inputs
- The current acting context present in the session: stated facts, assumptions, inferred file state, and prior decisions.
- The source of truth for each item being rechecked: repository files, tool output, or user-stated ground truth.
- Optional: a user-named subset to recheck. If omitted, recheck the full acting context.
## Procedure
1. Enumerate every item in the acting context: stated facts, assumptions, inferred file state, and prior decisions. Done when: every acting-context item is enumerated.
…
The line at the top of this page pins the label git:20260912.5c5b759, 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_zszntptuhh6fsljy
GET https://markdownregistry.com/api/v1/resolve?ref=outlinedriven/outline-driven-development/context-engineering
GET https://markdownregistry.com/api/v1/blob/d43afa075ba1f94f775573b061386400ea7e9a46507629819e1b8a72652f4ea8
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.
outlinedriven/outline-driven-development · .devin/skills/abi-and-calling-conventions/SKILL.md · Use when explaining System V AMD64, ARM AAPCS, RISC-V psABI, stack frames, variadic calls, or FFI register rules. Not…
outlinedriven/outline-driven-development · .devin/skills/abstract-well/SKILL.md · Use when the user wants to classify abstractions as useful, bad, or busy and keep one shallow level. Not for tasks…
outlinedriven/outline-driven-development · .devin/skills/adc-dac-baremetal/SKILL.md · Use when configuring ADC sampling time, DMA-driven ADC, calibration, or DAC channel setup on bare-metal MCUs. Not for…
outlinedriven/outline-driven-development · .devin/skills/address-sanitizer/SKILL.md · Use when building or running native code under AddressSanitizer, interpreting an existing ASan report, or debugging a…
outlinedriven/outline-driven-development · .devin/skills/af-xdp/SKILL.md · Use when creating AF_XDP sockets, configuring UMEM and XSK rings, writing an XDP redirect program, or choosing copy…
outlinedriven/outline-driven-development · .devin/skills/agent-environment-retrospective/SKILL.md · Use when a completed session needs an agent-environment retrospective. Not for an engineering retrospective from…
outlinedriven/outline-driven-development · .devin/skills/agent-surface-forge/SKILL.md · Use when asked to audit or repair agent surfaces (plugins, agents, skills, CLAUDE.md/AGENTS.md, docs, prompts…
outlinedriven/outline-driven-development · .devin/skills/agent-transcript/SKILL.md · Use when a redacted, trimmed agent transcript must be appended to a GitHub PR or issue body, with human approval and…
outlinedriven/outline-driven-development · .devin/skills/agents-md/SKILL.md · Use when a repo needs agent setup, AGENTS.md added or made lean, CLAUDE.md audited, or agent instructions scored or…
outlinedriven/outline-driven-development · .devin/skills/ai-collab-protocols/SKILL.md · Use when the user describes an AI workflow gap or uses an ambiguous cross-session reference such as ''the PR Bob…
outlinedriven/outline-driven-development · .devin/skills/all-scenarios-storm/SKILL.md · Use when a user wants to enumerate plausible designs, configurations, scenarios, and paths and diagram the field before…
outlinedriven/outline-driven-development · .devin/skills/analysis-artifacts/SKILL.md · Use when the user requests a deep dive, exploratory analysis, or data analysis on BigQuery. Not for credential…
addyosmani/agent-skills · skills/context-engineering/SKILL.md · Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching…
mvschwarz/openrig · packages/daemon/specs/agents/shared/skills/process/context-engineering/SKILL.md · Use when designing, reviewing, or debugging how an agent's context window gets filled, pruned, or shared — choosing…
mvschwarz/openrig · skills/_canonical/process/context-engineering/SKILL.md · Use when designing, reviewing, or debugging how an agent's context window gets filled, pruned, or shared — choosing…
a5c-ai/babysitter · library/methodologies/gsd/skills/context-engineering/SKILL.md · Context window monitoring and budget management. Keeps orchestrator at 15-30% context usage while subagents get full…
shashankswe2020-ux/whoop-mcp · .github/skills/context-engineering/SKILL.md · Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching…