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/learn-knowledgenpx skills add lookatitude/guild --skill learn-knowledgegit clone --depth 1 https://github.com/lookatitude/guildWhat 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 | $0.00229 | $0.05334 |
| Opus 5 | $0.00114 | $0.02667 |
| Sonnet 5 | $0.00046 | $0.01067 |
| Haiku 4.5 | $0.00023 | $0.00533 |
Grade A, and why
guild-learn-knowledge 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 — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use it
Use to build the deep multi-modal knowledge tier on top of the structural
KnowledgeGraph — the guild.knowledge_graph.v2 enrichment that the
code-structure half (guild:learn-graph stages 2–7) does not produce: a
topic→subtopic taxonomy, classified + labeled wiki_page nodes for
every .guild/wiki/ page, diagram nodes from mermaid
blocks and .svg files, and cross-modal evidenced_by / relates_to
edges that make any knowledge node reachable from any related one. Implements
the K-stage pipeline in .guild/spec/learn-knowledge-tier.md §Design (SC-1…SC-15).
This skill is invoked three ways, running one implementation (SC-8): a
single shared K1–K6 entrypoint is called by /guild:learn knowledge, the full
/guild:learn pipeline, and /guild:init --learn / defaults.auto_learn: true. There is no second knowledge-tier engine and no per-trigger branch that
changes output — that is what makes the projection byte-identical across
the three triggers at a given commit.
When not to use it
Not for the structural code graph + reverse-spec (guild:learn-graph owns
stages 2–7), the cheap-scan map (guild:learn-map), tour narration
(guild:learn-onboard), the per-run diff (guild:learn-diff), or a single
file/module explanation (guild:learn-explain). Not for querying an
already-built graph — that is the bounded kg-query retrieval path (wired into
guild:context-assemble) / guild:wiki-query. Not for ingesting a single
external source (guild:wiki-ingest). Never required for Init (Init stops at
the cheap-scan tier; this is lazy + gated like the deep graph).
Required inputs
.guild/indexes/knowledge-graph.json— the structural graph fromguild:learn-graph(file/function/class nodes + structural edges + layers). This skill enriches it intoguild.knowledge_graph.v2; it does not re-derive the structural half. If absent, escalate — runguild:learn-graphfirst; do not invent structure.- The resolved knowledge config —
resolveSettings({ cwd }).models.knowledge.*(maxDepth 8,maxBranching 12,minTopicImportance 0.4,relMinConf 0.5,maxFiles 3000,maxTokens 1_000_000,batchSize 20; defaults inscripts/learn/lib/schema.ts KNOWLEDGE_CONFIG_DEFAULTS, overridable in.guild/settings.json). Read it; never re-spell the numbers in prose. - The cost gate + lazy consent (SC-15) and the per-K-stage staleness verdict (SC-14) — both are deterministic scripts (below); the skill calls them and consumes their JSON verbatim, never re-deriving the decision.
- Frozen contracts bound by pointer only:
guild.knowledge_graph.v2(scripts/learn/lib/schema.ts; schema is canonical in the source — do not re-spell field names or version strings). The output-locations table is owned byguild:learn-map— referenced, never re-spelled.
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 First seen · 304 lines · 229 tokens per session scan A 612b22b27f12
guild-learn-knowledge is a skill published in the GitHub repository lookatitude/guild (7 stars, last pushed 2d ago), licensed MIT. It adds 229 tokens to every session and 5,334 once invoked, about $0.0011 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 2026-08-31.
Other skills, from other repositories
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
bigquery-ai-ml
Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform time-series forecasting, predict values, detect outliers or anomalies, find key drivers, perform semantic search or vector search, classify text, calculate similarity…
ondb
A logical analysis and reasoning tool for AI. Use when decomposing documents into structured knowledge, querying entities and relations, validating consistency, or indexing files. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", "analyze this document", entity CRUD, or cross-skill…
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
mixed-precision
Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.
sparse-autoencoder-training
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.