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 axiomantic/spellbook --skill assembling-contextgit clone --depth 1 https://github.com/axiomantic/spellbookWrote 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/axiomantic/spellbook/assembling-context)<a href="https://agentmods.dev/skills/axiomantic/spellbook/assembling-context"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/assembling-context/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/axiomantic/spellbook/assembling-context"><img src="https://agentmods.dev/badge/skills/axiomantic/spellbook/assembling-context.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00056 | $0.01068 |
| Opus 5 | $0.00028 | $0.00534 |
| Sonnet 5 | $0.00011 | $0.00214 |
| Haiku 4.5 | $0.00006 | $0.00107 |
Grade A, and why
assembling-context 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 7d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Assembly
Invariant Principles
- Tier 1 Never Truncates: Essential context survives any budget pressure
- Budget Before Assembly: Calculate budget FIRST, then select
- Purpose Drives Selection: Design context differs from implementation differs from review
- Recency Over Completeness: Recent feedback beats historical context
- Summarize, Don't Truncate: Intelligent summarization preserves signal
- Integration Points are Tier 1: Interface contracts are essential
Inputs / Outputs
| Input | Required | Description |
|---|---|---|
purpose |
Yes | design, implementation, review, handoff, subagent |
token_budget |
Yes | Maximum tokens available |
source_context |
Yes | Raw context to select from |
| Output | Description |
|---|---|
context_package |
Tiered context ready for injection |
truncation_report |
What was excluded and why |
Context Tiers
Over budget: remove Tier 3 first, then Tier 2. Never remove Tier 1.
| Tier | Budget | Content | Examples |
|---|---|---|---|
| 1: Essential | 40-60% | Active instructions, user decisions, current artifact, interface contracts, blocking issues | Task spec, APIs, unresolved feedback |
| 2: Supporting | 20-35% | Recent learnings, patterns, prior feedback, success criteria | Last 2-3 iterations, codebase patterns |
| 3: Reference | 10-20% | Historical context, rejected alternatives, verbose docs | Early iterations, full docs (summarize instead) |
Purpose-Specific Packages
| Purpose | Tier 1 Focus | Budget Split | Use With |
|---|---|---|---|
| Design | Requirements, decisions, constraints, integration points | 50/30/20 | design-exploration, writing-plans |
| Implementation | Task spec, acceptance criteria, interfaces, test expectations | 60/25/15 | test-driven-development, executing-plans |
| Review | Code diff, requirements traced, test results | 55/30/15 | code-review, fact-checking |
| Handoff | Current position, pending work, active decisions, blocking issues | 70/20/10 | session boundaries, compaction |
| Subagent | Task, constraints, expected output format | 65/25/10 | dispatching-parallel-agents |
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.
- 7d ago First seen · 105 lines · 56 tokens per session scan A 60131fdbb354
assembling-context is a skill published in the GitHub repository axiomantic/spellbook (10 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 1,068 once invoked, about $0.0003 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
stacks
Load stack-specific knowledge (conventions, exact lint/test/build commands, common failure patterns) onto the current role agent for the project's detected tech stack(s) — Next.js, React Native, Spring Boot, FastAPI, Django, Rust, etc. Use at the start of any task in an unfamiliar or newly-onboarded repo, or whenever…
opencode-export
Export opencode sessions to self-contained HTML + JSON archives for sharing, review, or backup. Use when the user wants to save, archive, or share their AI coding session history.
profile
Read the user's ENTIRE Claude Code message history with a multi-agent workflow, mine the working preferences that recur across almost all their tasks, verify each against the whole corpus, and distill them into a CLAUDE.md block so they never have to repeat them. Language-agnostic. Triggers: 'analyze how I use…
caveman
Ultra-compressed communication mode. Cuts token usage 75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or…
memstack-automation-n8n-workflow-builder
Use this skill when the user says 'n8n workflow', 'build a workflow', 'automation workflow', 'connect services', or needs visual workflow design with node mapping, data transformations, and error handling for n8n. Do NOT use for standalone webhook endpoints or cron jobs.
feishu-openapi-skill
Operate Feishu or Lark IM APIs through UXC with a curated OpenAPI schema, tenant-token bearer auth, and chat/message guardrails.