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 Wh0FF24/whoff-agents --skill context-anchorgit clone --depth 1 https://github.com/Wh0FF24/whoff-agentsWrote 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/wh0ff24/whoff-agents/context-anchor)<a href="https://agentmods.dev/skills/wh0ff24/whoff-agents/context-anchor"><img src="https://agentmods.dev/badge/skills/wh0ff24/whoff-agents/context-anchor.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 5.1 | $0.00036 | $0.00587 |
| Opus 5 | $0.00018 | $0.00293 |
| Sonnet 5 | $0.00007 | $0.00117 |
| Haiku 4.5 | $0.00004 | $0.00059 |
Grade A, and why
context-anchor 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 8d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Anchor Skill
You are establishing a working reference — a compact, accurate snapshot of what is true right now so the rest of this session (and the next one) doesn't drift.
What You Will Do
-
Scan the current session for:
- What was being built / fixed / investigated
- What decisions were made and why
- What was tried and ruled out
- What the next concrete action is
-
Write the anchor in this exact format to a file at
<project-root>/.claude/anchor.md:
# Context Anchor — <ISO timestamp>
## What's true right now
- [1-sentence state of the work]
- [Key decision made: what and why]
- [What was tried and didn't work, if anything]
## The working reference
> [One sentence that a new agent could act on immediately]
## Next action
- [ ] <exact next step, file:line if applicable>
- Echo the anchor to the user so they can verify it before trusting it.
Rules
- No filler. Every line must be load-bearing. If you can delete a line without losing information, delete it.
- Concrete over vague. "Fix auth middleware at
src/auth.ts:47" beats "fix the auth issue." - Decisions get a why. "Chose JWT over sessions — no server-state requirement" not just "chose JWT."
- Ruled-out paths go in. Future agents waste tokens re-exploring dead ends. Write them down.
When to Use
- Before switching tasks mid-session
- Before handing off to another agent (Leonidas, Diomedes, any hero)
- At the start of a new session when context is stale
- Any time you notice yourself re-reading earlier messages to remember state
Why This Exists
Claude Code sessions accumulate noise. Old tool results, retracted approaches, superseded decisions — they all stay in context and create cascading context drift: the model starts reasoning from stale state because the signal is buried. An anchor clears the noise and makes the working reference explicit.
This skill is free. The full Atlas Starter Kit ($97) includes 12 more production skills covering agent orchestration, output verification, systematic debugging, parallel dispatch, and the complete PAX protocol for multi-agent coordination.
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.
- 8d ago First seen · 61 lines · 36 tokens per session scan A 1f1966389d19
context-anchor is a skill published in the GitHub repository Wh0FF24/whoff-agents (2 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 587 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
agentsview-usage
Search prior session history to recall how similar work was handled before. Use when you want to leverage a past approach, check prior experience on a topic, answer "how was this handled before", or cross-verify current handling against precedent from earlier sessions.
honcho
Configure and troubleshoot Honcho memory for Hermes.
pinecone-research
Agent RAG and long-term memory with Pinecone.
crewai-multi-agent
Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies…
llm-wiki
Karpathy's LLM Wiki: build/query interlinked markdown KB.
qmd
Hybrid local search over notes, docs, and transcripts.