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 guia-matthieu/clawfu-skills --skill context-engineeringgit clone --depth 1 https://github.com/guia-matthieu/clawfu-skillsWrote 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/guia-matthieu/clawfu-skills/context-engineering)<a href="https://agentmods.dev/skills/guia-matthieu/clawfu-skills/context-engineering"><img src="https://agentmods.dev/badge/skills/guia-matthieu/clawfu-skills/context-engineering/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/guia-matthieu/clawfu-skills/context-engineering"><img src="https://agentmods.dev/badge/skills/guia-matthieu/clawfu-skills/context-engineering.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00051 | $0.01750 |
| Opus 5 | $0.00026 | $0.00875 |
| Sonnet 5 | $0.00010 | $0.00350 |
| Haiku 4.5 | $0.00005 | $0.00175 |
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 9d 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 — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Engineering
Overview
Core principle: Context is a finite resource with diminishing returns. Find the smallest high-signal token set, not the largest.
200K tokens is shared space: system prompt + conversation history + your processing. As context grows, performance degrades predictably.
When to Use
- Session > 30 minutes or 50k+ tokens
- Instructions being ignored or forgotten
- Repeated clarifications needed
- Planning multi-agent workflows
- Preparing handoffs between sessions
Quick Reference
| Problem | Symptom | Fix |
|---|---|---|
| Lost-in-middle | Mid-conversation instructions ignored | Move critical info to start/end |
| Context poisoning | Errors compounding, hallucinations referenced | Summarize and reset |
| Context distraction | Irrelevant info degrading performance | Prune aggressively |
| Context confusion | Conflicting guidance causing inconsistency | Consolidate instructions |
Degradation Patterns
1. Lost-in-Middle Effect
Information in context middle gets 10-40% lower recall than edges.
[START - High attention]
↓
[MIDDLE - Low attention zone] ← Instructions here get ignored
↓
[END - High attention]
Fix: Strategic placement
- Critical instructions → START (system prompt, first user message)
- Recent decisions → END (last few messages)
- Reference material → MIDDLE (acceptable for lookup, not instructions)
2. Context Poisoning
Early hallucination gets referenced → compounds → becomes "fact".
Symptoms:
- Confident statements contradicting earlier facts
- "As we discussed..." referencing things never said
- Circular reasoning citing own previous errors
Fix: Checkpoint and summarize
Every 10-15 exchanges, create explicit checkpoint:
"Let me summarize what we've established:
1. [Verified fact]
2. [Verified fact]
3. [Decision made]
Continuing from here..."
3. Context Distraction
Irrelevant tokens compete for attention budget.
Symptoms:
- Responses reference unrelated earlier topics
- Focus drifts from current task
- Unnecessary caveats about old context
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.
- 9d ago First seen · 265 lines · 51 tokens per session scan A 40469fdcf962
context-engineering is a skill published in the GitHub repository guia-matthieu/clawfu-skills (149 stars, last pushed 5mo ago), licensed MIT. It adds 51 tokens to every session and 1,750 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
error-log
Apply when learning from a mistake. Central memory of past errors and derived rules; consult before logging a new error to avoid duplicates.
skill-everything
Git-versioned agent memory — agents that never make the same mistake twice.
ads-creative-development
How to produce ad creative that converts at performance scale. Hook patterns, format selection, video pacing, variation systems, sequential testing methodology, fatigue detection, brand-voice alignment without conversion dilution, and platform-specific creative norms. Triggers on ad creative, ad design, hook patterns…
ads-performance-analytics
How to read paid media dashboards without fooling yourself. Attribution models, platform reporting quirks, multi-platform reconciliation, ROAS vs LTV horizon traps, statistical noise in performance metrics, incrementality testing, and the failure modes that produce expensive lessons. Triggers on read paid media…
paid-media-strategy
A discipline for running paid media that does not light money on fire. Hypothesis writing for paid spend, channel selection, budget allocation, audience targeting, bid strategy, campaign types, what NOT to spend on, attribution reality, and the failure modes that produce expensive lessons. Triggers on paid media…
mem-search
Search past coding sessions using natural language. Finds relevant observations, decisions, and context from previous work.