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 liza-mas/liza --skill context-engineeringgit clone --depth 1 https://github.com/liza-mas/lizaWrote 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/liza-mas/liza/context-engineering)<a href="https://agentmods.dev/skills/liza-mas/liza/context-engineering"><img src="https://agentmods.dev/badge/skills/liza-mas/liza/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/liza-mas/liza/context-engineering"><img src="https://agentmods.dev/badge/skills/liza-mas/liza/context-engineering.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 | $0.00123 | $0.03747 |
| Opus 5.5 | $0.00049 | $0.01499 |
| Sonnet 5.5 | $0.00025 | $0.00749 |
| Haiku 4.5 | $0.00012 | $0.00375 |
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 1mo 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 — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Engineering
Scope
Analyze only §BRAND_PROJECT_DIRNAME§/agent-prompts/ and §BRAND_PROJECT_DIRNAME§/agent-outputs/ unless the user names other artifacts.
This skill is complementary to §BRAND_BINARY_NAME§-logs: §BRAND_BINARY_NAME§-logs finds operational failures and token/tool patterns; this skill explains whether the prompt and context design caused or amplified those patterns.
Protocol
1. Inventory Before Reading
Run the corpus indexer first:
python3 skills/context-engineering/scripts/context-corpus-index.py §BRAND_PROJECT_DIRNAME§
Use the generated index as the primary source for mechanical discovery: inventory, prompt/output pairing, size and pressure signals, outcome signals, common tools, MCP usage, and sample selection. The index is not evidence of causality by itself.
The indexer supports both Claude rich stream-json logs and Codex sparse item.completed logs. Check the reported format counts before assuming which fields are available.
Use indexer options deliberately:
python3 skills/context-engineering/scripts/context-corpus-index.py §BRAND_PROJECT_DIRNAME§ --json
python3 skills/context-engineering/scripts/context-corpus-index.py §BRAND_PROJECT_DIRNAME§ --max-pair-minutes 30
python3 skills/context-engineering/scripts/context-corpus-index.py §BRAND_PROJECT_DIRNAME§ --sample-limit 25
- Use
--jsonwhen exact pair metadata, token fields, or full metrics are needed. - Use
--max-pair-minutesto control how strict same-role timestamp pairing should be. - Use
--sample-limitto expand or shrink top lists and the sampling plan.
If a §BRAND_BINARY_NAME§-logs report or analyzer output is available, use it as the first sampling guide. Prioritize roles, runs, or timestamps with repeated tool failures, broad tool-result volume, duplicated task-local material, growing prompts, low cache reuse for expected-stable prefixes, or blocked/rejected task outcomes.
If §BRAND_BINARY_NAME§-logs and context-engineering evidence disagree, report the disagreement explicitly and keep the narrower claim supported by direct prompt/output evidence. Example: §BRAND_BINARY_NAME§-logs may correctly flag token pressure while prompt shape is not the cause.
What ships with it
1 file 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.
- 1mo ago Changed · +1 lines 594a71cc29ee
- 1mo ago First seen · 266 lines · 123 tokens per session scan A b4bedb34cd84
context-engineering is a skill published in the GitHub repository liza-mas/liza (410 stars, last pushed today), licensed Apache-2.0. It adds 123 tokens to every session and 3,747 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.