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/paruff/ufawkesai/context-engineeringnpx skills add paruff/uFawkesAI --skill context-engineeringgit clone --depth 1 https://github.com/paruff/uFawkesAIWrote 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/paruff/ufawkesai/context-engineering)<a href="https://agentmods.dev/skills/paruff/ufawkesai/context-engineering"><img src="https://agentmods.dev/badge/skills/paruff/ufawkesai/context-engineering.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 | $0.00048 | $0.01775 |
| Opus 5 | $0.00024 | $0.00888 |
| Sonnet 5 | $0.00010 | $0.00355 |
| Haiku 4.5 | $0.00005 | $0.00178 |
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 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Context Engineering
Load trigger:
"load context-engineering skill"> DORA: AI Capability 3 (AI-accessible internal data) Token cost: Low
Purpose
Move AI tools from generic assistants to specialized experts by connecting them to internal documentation and codebase structure. "Context engineering" is the practice of deliberately managing what internal knowledge is available to AI tools at session start — not just what prompt you give them.
DORA AI Capabilities Model v2025.1: "Connecting AI to your internal documentation and codebases moves it from a generic assistant to a specialized expert."
This skill eliminates the "re-discover context every session" tax — particularly costly at 2hrs/day across an 8-repo portfolio.
Graphify Variant Note
⚠ Confirm before use: Two different tools share the name "graphify":
safishamsi/graphify— knowledge graph from code structurerhanka/graphify— graph visualization tool
These have different CLI syntax. This skill uses [graphify-cli] as a placeholder.
Replace with the actual command after confirming which variant is installed:
# Check which is installed
which graphify && graphify --version
# Or check package.json / pyproject.toml for the dependency
Minimum Corpus per Repo
Every uFawkes* repo must maintain these files for AI-accessible context. Missing files are flagged as corpus gaps, not silently ignored.
| File | Required | Purpose |
|---|---|---|
README.md |
✅ Mandatory | What this is, quick start, current status |
AGENTS.md |
✅ Mandatory | Agent suite, skill list, handoff protocol |
ARCHITECTURE.md or docs/ARCHITECTURE.md |
✅ Mandatory | System design, component relationships |
CONTRIBUTING.md |
✅ Mandatory | How to contribute — must not be a placeholder |
AI_STANCE.md |
✅ Mandatory | AI policy (see ai-stance skill) |
tests/README.md or equivalent |
✅ Mandatory | How to run tests, what they cover |
CHANGELOG.md |
✅ Mandatory | Release history |
DORA-event-format.md |
⚠ Required when uFawkesObs wired | Deployment event schema for DORA metrics |
docs/PROMPT_LIBRARY.md |
Optional | Tested prompt templates (see uFawkesObs) |
What ships with it
3 files 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 · 153 lines · 48 tokens per session scan A 7ed570103cca
context-engineering is a skill published in the GitHub repository paruff/uFawkesAI (2 stars, last pushed 12d ago), licensed MIT. It adds 48 tokens to every session and 1,775 once invoked, about $0.0002 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
continual-learning
Orchestrate continual learning by delegating transcript mining to agents-memory-updater and writing durable memory to local JSON (never root AGENTS.md Learned sections). USE WHEN continual learning, mine prior chats, maintain agent memory, or the stop hook triggers this skill.
learn
Review the current conversation and update project knowledge artifacts - common-gotchas.md (bug patterns), AGENTS.md (conventions), agent memory (cross-session). Use when asked to '/learn', 'what did we learn', 'capture lessons', 'update common-gotchas'.
save-learning
Use when you learned something durable — a decision, a hard-won lesson, a useful reference. Captures it into the memory wiki so it compounds.
save-memory
Persist newly-learned facts from the current session into the memory pyramid. Scans the conversation for durable information, finds the right file, deduplicates, and writes back. Use when the user says "remember this", "save it", "for next time", or when a non-obvious fact surfaced that a future session would ask…
wrap-up
Update memory/ACTIVE.md with the state of the current session — what was worked on, what's done, what's next, what's blocked — so the next session can pick up without re-learning context. Run at session end or when switching to an unrelated task.
latent-briefing
This skill should be used when the user asks to "share memory between agents", "KV cache compaction for multi-agent", "orchestrator worker context", "latent briefing", "reduce worker tokens", "cross-agent memory without summarization", or discusses Attention Matching compaction, recursive language models with workers…