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/lookatitude/guild/v1npx skills add lookatitude/guild --skill v1git clone --depth 1 https://github.com/lookatitude/guildWrote 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/lookatitude/guild/v1)<a href="https://agentmods.dev/skills/lookatitude/guild/v1"><img src="https://agentmods.dev/badge/skills/lookatitude/guild/v1.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.06086 |
| Opus 5 | $0.00000 | $0.03043 |
| Sonnet 5 | $0.00000 | $0.01217 |
| Haiku 4.5 | $0.00000 | $0.00609 |
Grade A, and why
guild-context-assemble 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 4d 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 — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
guild:context-assemble
Implements the context-assembly contract (minimum viable context per specialist). Runs after guild:plan has produced an approved .guild/plan/<slug>.md, invoked per-lane by guild:execute-plan immediately before each specialist dispatch. One bundle per specialist per run.
The rule
A specialist's authoritative task brief is the union of three layers — nothing more. No project-wide dumps. No sibling-specialist lanes unless the plan declares an upstream contract via depends-on:.
| Layer | Content | Size target |
|---|---|---|
| Universal | guild:principles + wiki/context/project-overview.md + wiki/context/goals.md |
~400 tokens |
| Role-dependent | wiki/standards/*.md matching the role (per §9.2 mapping) + 2–4 most-relevant entity pages from wiki/entities/ matching the task domain |
~800–1500 tokens |
| Task-dependent | The specialist's lane block from .guild/plan/<slug>.md + named refs (concepts, decisions, products the spec/plan names) + upstream contracts pulled from each depends-on: task's completed output + active decisions from wiki/decisions/ touching the task domain + (when a brownfield graph exists) a bounded KnowledgeGraph retrieval sub-source — see ## Graph retrieval + (when the run is attached to an initiative) the initiative-summary slot — see ## Initiative-summary slot |
~800–1500 tokens |
Total target: ~3k tokens. Hard cap: 6k (enforced in ## Size budget).
Role mapping
Select standards and typical products by the specialist's role group:
| Role group | Standards loaded | Typical products loaded |
|---|---|---|
| Engineering (architect, backend, frontend, qa, devops, data) | wiki/standards/coding-standards.md |
wiki/entities/products/<component>.md for each component the lane explicitly names |
| Writing (copywriter, tech-writer) | wiki/standards/writing-voice.md + wiki/standards/branding.md |
wiki/entities/products/<feature>.md if the deliverable is user-facing |
| Social / SEO (seo, social) | wiki/standards/writing-voice.md + wiki/standards/branding.md + wiki/standards/seo-rules.md |
wiki/entities/products/<feature>.md if the deliverable is user-facing |
| Commercial (marketing, sales) | wiki/standards/branding.md + wiki/standards/pricing-policy.md |
wiki/entities/products/*.md for any product the lane references |
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.
- 4d ago First seen · 293 lines · 0 tokens per session scan A 626457706e31
guild-context-assemble is a skill published in the GitHub repository lookatitude/guild (7 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 6,086 tokens. 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 2026-08-31.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…