Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add OutlineDriven/outline-driven-development --skill context-engineeringgit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/outlinedriven/outline-driven-development/context-engineering)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/context-engineering"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/context-engineering/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/context-engineering"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/context-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00037 | $0.00665 |
| Opus 5 | $0.00018 | $0.00332 |
| Sonnet 5 | $0.00007 | $0.00133 |
| Haiku 4.5 | $0.00004 | $0.00067 |
Grade A, and why
context-engineering scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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
- Enumerate every item in the acting context: stated facts, assumptions, inferred file state, and prior decisions. Done when: every acting-context item is enumerated.
- For each item, recheck it against its source of truth by the narrowest action that settles it: read the file, re-run the tool, or ask the user. Classify the item as current, stale, or contradicted. Done when: every item is classified current, stale, or contradicted.
- Drop stale and contradicted items from the acting context. Replace a dropped item with the corrected value only when the source of truth supplies one. Done when: stale and contradicted items are dropped and replaced where a corrected value exists.
- Remove redundant or duplicate items so the acting context holds only items that are provably current and needed for the remaining work. Done when: no redundant or duplicate items remain.
- Tell the user which items were dropped and why, and identify any item that could not be settled because its source of truth was unreachable. Done when: dropped items and reasons are reported and unsettled items are identified.
- Optionally write a scratch state note recording the settled context and the dropped items. Do not touch any project file. Done when: the scratch note is written or skipped, and no project file is touched.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago Changed · -20 tokens per session 21804a6c8637
- 4d ago First seen · 40 lines · 57 tokens per session scan A 4f33a082a942
context-engineering is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 37 tokens to every session and 665 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
autolearn
Use when a verified non-trivial fix lands or existing solution docs need refresh. Not for unverified fixes.
consolidate-to-one-home
Fold a scattered fact into a single home and point the rest at it. Use when the same rule, constant, or definition is restated in several files, or the user says "consolidate this", "make this the single source of truth", or "ssotize this". The consolidation is proposed and approved before any edit lands. To…
memory-clean
Audit memory directory for structural issues (orphans, dangling refs, duplicates, missing sections, oversized entries) and staleness against session-history transcripts; report-first, fix-on-confirmation. Use when the user says "audit memory", "memory hygiene", or "find stale/duplicate memories".
memory-update
Scan agent's session-history transcripts for save-worthy signals (corrections, preferences, decisions, references), propose and write auto-memory files with valid frontmatter and MEMORY.md entry. Use when the user says "save this to memory", "remember that", or "scan this session for memories".
memory-sanitize
Produce share-safe copies of memory files under /tmp with PII redacted (paths, emails, session IDs, dates) and credentials scanned (tokens, keys); never mutates originals. Use when the user says "sanitize memory for sharing", "redact memory PII", or "scan memory for credentials".
shellm
Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.