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 5.5 | $0.00022 | $0.00427 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo ago First seen · 105 lines · 56 tokens per session scan A 60131fdbb354
assembling-context is a skill published in the GitHub repository axiomantic/spellbook (11 stars, last pushed yesterday), licensed MIT. It adds 56 tokens to every session and 1,068 once invoked, about $0.0002 per session on Opus 5.5. 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
batch
Execute batch operations on multiple files in parallel. Automatically discovers files, splits into chunks, and processes with parallel worker agents. Use /batch followed by operation and file pattern. For many independent single-turn transforms (translate/rewrite/extract each file into a new file) that can wait…
batch-api
Prepare a many-file, single-turn transform (translate, rewrite, extract) as a plan and submit it to the asynchronous, half-price DashScope Batch API; results are delivered as new files hours later. Invoke explicitly with /batch-api.
loop
Create a loop that runs a prompt now and follows up either on a fixed schedule or through self-paced wakeups. Usage - /loop check the build, /loop 5m check the build, /loop check the PR every 30m. /loop list to show jobs, /loop clear to cancel all.
openrig-herdr
Use when opening OpenRig fleet terminals as a herdr wall — turning a rig, pod, mission, slice, or saved view into live interactive agent tiles via rig terminal, watching another rig read-only, or driving herdr on an agent's request ("open all my rigs + a mission as views"). Covers the rig terminal open|views|status…
mission-slice-sop
Use when starting, building, handing off, restoring, or closing a mission or slice under the default lightweight SDLC.
community
Use when building or running a persistent two-way community space — Discord, Telegram, Circle: platform choice, structure, onboarding, native→bot→human moderation, rituals, growth loops, health metrics. NOT churn of paying product customers (that is retention), NOT broadcast email (that is newsletter), NOT one live…