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/fending/context-engineering/onboardnpx skills add fending/context-engineering --skill onboardgit clone --depth 1 https://github.com/fending/context-engineeringWhat 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 | $0.00035 | $0.01059 |
| Opus 5 | $0.00017 | $0.00530 |
| Sonnet 5 | $0.00007 | $0.00212 |
| Haiku 4.5 | $0.00003 | $0.00106 |
Grade A, and why
onboard 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onboard
Discover and summarize the project's context structure so you can orient quickly.
What This Skill Does
-
Discover context files at all levels:
- Global (user-level AGENTS.md or tool-specific equivalent like
~/.claude/CLAUDE.md) - Project root (
AGENTS.mdas primary, check forCLAUDE.mdsymlink) - Subdirectories (any nested
AGENTS.mdfiles) - Context directory (
context/or similar with multiple files) - Agent definitions (
examples/agents/,examples/agent-teams/) - Skills (
.claude/skills/or equivalent) - Hooks (
.claude/settings.jsonhook configurations)
- Global (user-level AGENTS.md or tool-specific equivalent like
-
Summarize each file with a one-line description and last modification date. Focus on what each file tells the AI to do differently -- boundaries, conventions, workflow instructions.
-
Flag potential staleness:
- References to packages not in
package.json/requirements.txt/go.mod - References to directories that don't exist on the filesystem
- Build or test commands that don't match actual scripts
- Agent state files with timestamps older than 30 days
- References to packages not in
-
Produce a context map -- a navigation guide that tells agents which files to read depending on the task, without front-loading everything. Group discovered files by when they're relevant:
- The root AGENTS.md covers boundaries, stack, and commands -- always applicable.
- Subdirectory AGENTS.md files apply when working in the directories they govern.
- Context directory files apply when investigating specific concerns (architecture, API surface, data model).
- Agent definitions and state files apply only when running those specific workflows.
The map is the last section of the output. It answers "what should I read before starting this task?" not just "what exists?"
Report findings conversationally. This is orientation, not an audit -- surface what matters for starting work, not an exhaustive inventory.
When to Use
- At the start of a new session on an unfamiliar project
- When a new contributor (human or AI) joins the project
- After major refactoring that may have changed project structure
- When you're unsure what context files exist or how they relate
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 · 81 lines · 35 tokens per session scan A ea5e40486db9
onboard is a skill published in the GitHub repository fending/context-engineering (11 stars, last pushed 5mo ago), licensed MIT. It adds 35 tokens to every session and 1,059 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 2026-08-30.
Other skills, from other repositories
ccc
This skill should be used when code search is needed (whether explicitly requested or as part of completing a task), when indexing the codebase after changes, or when the user asks about ccc, cocoindex-code, or the codebase index. Trigger phrases include 'search the codebase', 'find code related to', 'update the…
feature-flags-audit
Audit and inventory all feature flags declared in the Packmind codebase. Use when the user asks to list, audit, review, or inventory feature flags, asks which flags are active, wants to know what a flag gates, or asks which flags are opened to a given domain/user. Produces a synthetic markdown table with each flag…
packmind-create-standard
Guide for creating coding standards via the Packmind CLI. This skill should be used when users want to create a new coding standard (or add rules to an existing standard) that captures team conventions, best practices, or coding guidelines for distribution to GitLab Duo.
create-run-e2e-tests
Guide for writing and running new Playwright end-to-end tests in the apps/e2e-tests/ directory of the Packmind monorepo. Use this skill whenever you add or modify a spec that drives the real frontend and API — for example testing a user flow, a new page/route, a feature behind a flag, or a UI behavior end-to-end.…
working-with-pm-design-kit
This skill provides guidance for using the Packmind UI component library (@packmind/ui). It should be used when building or modifying frontend UI with PM-prefixed components, working with Chakra UI in the Packmind codebase, or when questions arise about available components, theming, or layout patterns. Triggers on…
working-with-playground-app
This skill provides guidance for building UI/UX prototypes in the Packmind playground app. It should be used when creating a new prototype, iterating on an existing prototype, or working with files in apps/playground/. Triggers on mentions of "playground", "prototype", or direct work within the apps/playground/…