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 strikersam/autonomous-ai-agency --skill context-primegit clone --depth 1 https://github.com/strikersam/autonomous-ai-agencyWrote 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/strikersam/autonomous-ai-agency/context-prime)<a href="https://agentmods.dev/skills/strikersam/autonomous-ai-agency/context-prime"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/context-prime/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/strikersam/autonomous-ai-agency/context-prime"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/context-prime.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00028 | $0.00666 |
| Opus 5.5 | $0.00011 | $0.00266 |
| Sonnet 5.5 | $0.00006 | $0.00133 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
context-prime 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 7d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: context-prime
Purpose
Prime Claude with deep repository context before starting any significant task. Ensures Claude has a full mental model of the codebase architecture, conventions, and constraints before writing a single line of code.
Trigger
Use at the start of:
- A new coding session on an unfamiliar area
- A complex feature that touches many files
- A debugging session for a hard-to-reproduce bug
- Onboarding to a new repository
Process
Step 1: Read Core Docs
In order:
CLAUDE.md— primary instructions and conventionsREADME.md— project overview and purposeTOOLS.md— available toolingagent/CLAUDE.md— agent-specific context (if exists)- Any
docs/folder overview files
Step 2: Map the Architecture
Scan the top-level directory structure. For each major directory:
- Identify its purpose
- Note key files within it
- Understand how it connects to other directories
Build a mental map: [module] → [responsibility] → [interfaces with]
Step 3: Find Conventions
Look for patterns across 5-10 representative files:
- Naming conventions (files, functions, classes, variables)
- Import organization style
- Error handling patterns
- Testing patterns (test file location, naming, fixtures)
- Comment/docstring style
- Type annotation usage
Step 4: Understand Data Flow
Trace the main data flow through the system:
- Entry points (API routes, CLI commands, event handlers)
- Core processing logic
- Storage/persistence layer
- Output/response formation
Step 5: Identify Constraints
Note any explicit constraints from CLAUDE.md or comments:
- Performance-sensitive areas
- Security boundaries
- Deprecated patterns to avoid
- In-progress refactors to be aware of
Step 6: Declare Readiness
Output a structured context summary:
## Context Prime Complete
### Project
[1-2 sentence description of what this project does]
### Architecture
- [Layer/Module]: [responsibility]
- [Layer/Module]: [responsibility]
### Key Conventions
- [Convention]: [example]
- [Convention]: [example]
### Data Flow
[Entry] → [Processing] → [Storage] → [Output]
### Constraints to Respect
- [Constraint]
- [Constraint]
### Ready for Task
I have sufficient context to begin. Proceeding with: [task description]
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.
- 7d ago Changed · +4 lines · +28 tokens per session 6495bdc12750
- 1mo ago First seen · 91 lines · 0 tokens per session scan A de7f3e592d4c
context-prime is a skill published in the GitHub repository strikersam/autonomous-ai-agency (11 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 666 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
memclaw
The agent's persistent long-term memory — the only knowledge that survives across sessions, shared across the fleet under access control. Consult it at the start of a task to recall prior decisions, findings, and rules before acting, and write outcomes, decisions, and lessons as work completes. Use whenever a caura…
mem0-integration
Mem0 memory layer integration for AI agents. Implement persistent, semantic memory for long-term context retention and personalization.
state-management
STATE.md reading, writing, and field-level updates. Provides cross-session state persistence via .planning/STATE.md with structured fields for current task, completed phases, blockers, decisions, and quick tasks.
context-preservation
State capture and restore across context window compactions. Monitors usage thresholds and serializes quality, task, and spec state for seamless continuation.
persistent-memory
Observation capture and retrieval across sessions. Stores decisions, discoveries, and bugfix patterns. Searchable via tags and relevance scoring.
context-management
Project context loading, isolation, and persistent state management across CCPM sessions.