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 agentmods add skills/galando/temper/context-engineeringnpx skills add galando/temper --skill context-engineeringgit clone --depth 1 https://github.com/galando/temperWhat 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 | $0.00018 | $0.01301 |
| Opus 5 | $0.00009 | $0.00651 |
| Sonnet 5 | $0.00004 | $0.00260 |
| Haiku 4.5 | $0.00002 | $0.00130 |
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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Engineering
Version: 1.0.0 Last Updated: 2026-05-12
Overview
Context engineering is the discipline of loading the right information, in the right order, at the right time. AI coding agents have finite context windows. Loading too much wastes tokens and dilutes attention. Loading too little causes hallucinations and missed dependencies.
This skill provides a hierarchical loading strategy that maximizes signal per token:
Priority 1: rules → pack rules, stack conventions, guardrails
Priority 2: arch → module boundaries, dependency graph, entry points
Priority 3: source → specific files relevant to the current task
Priority 4: errors → recent failures, test output, runtime errors
Priority 5: conversation → prior decisions, user intent, stakeholder context
When to Use
- Start of every
/temperstage (plan, design, build, review, check, fix) - Before making changes to unfamiliar code
- When resuming a session from saved state
- When context feels stale (agent is repeating itself or missing obvious facts)
Process
Step 1: Determine Task Scope
Before loading anything, answer:
- What am I doing? (fixing a bug, adding a feature, reviewing code)
- What files am I likely to touch? (from tasks.md or plan.md)
- What do I already know? (from current context or build-state.json)
This takes 10 seconds and prevents loading 80% of files you won't use.
Step 2: Load Rules (always first)
Load in this order:
.claude/temper.config— enabled packs, stack, review settings.claude/packs/{enabled-pack}/rules.md— only enabled packs.claude/packs/stacks/{detected-stack}.md— stack-specific patterns (if exists).claude/CLAUDE.md— project conventions
Budget: ~200 lines total. If packs exceed this, load only the packs scoped to the current phase.
Step 3: Load Architecture (if touching unfamiliar code)
- Start with the file you need to change
- Trace dependencies: what does it import? What imports it?
- Stop at 2 hops — do not traverse the entire dependency graph
- If
plan.mdexists: read the file list section only (not the full plan)
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 First seen · 126 lines · 18 tokens per session scan A 8a3a2de5c808
context-engineering is a skill published in the GitHub repository galando/temper (15 stars, last pushed 3d ago), licensed MIT. It adds 18 tokens to every session and 1,301 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…