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/manager-dot-dev/manager-skills/em-contextnpx skills add manager-dot-dev/manager-skills --skill em-contextgit clone --depth 1 https://github.com/manager-dot-dev/manager-skillsWhat 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 | $0.00095 | $0.01452 |
| Opus 5 | $0.00048 | $0.00726 |
| Sonnet 5 | $0.00019 | $0.00290 |
| Haiku 4.5 | $0.00010 | $0.00145 |
Grade A, and why
em-context 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EM Context
This is the foundation skill. Its purpose is to capture your team, org, and individual direct report context so every other skill can work with your specific situation rather than generic advice.
This skill is not meant to be the main thing you invoke every day. It is the shared memory layer for the other EM skills.
File Structure
.agents/
├── em-context.md # Your team and org context
└── reports/
├── alice.md # One file per direct report
├── bob.md
└── carol.md
How to Use
Team context: Create .agents/em-context.md with your team and org context. All EM skills read this first.
Direct report profiles: Create .agents/reports/[firstname].md for each direct report. Skills like 1on1s, feedback, and performance-reviews will look for this file when you mention a person by name.
If files don't exist, ask the user for the relevant context before proceeding.
When other skills learn durable new context, they should update these files automatically. Treat them as living memory, not static setup files.
Bootstrapping Missing Context
If there is no .agents/em-context.md yet, do not keep giving generic advice forever. Ask for a minimal manager profile first, create the file, and then continue.
Minimum manager profile to collect:
- role/title
- team size
- team mission or area of ownership
- current challenge or priority
If a specific person comes up and there is no .agents/reports/[name].md yet, ask for a minimal profile for that person first, create the file, and then continue.
Minimum direct report profile to collect:
- title or level
- tenure on the team
- strengths
- current challenge, growth area, or reason they came up
Do not wait for a perfect profile. Save the minimum useful context first, then enrich it over time as new conversations reveal more.
Auto-Update Rules
All EM skills should use em-context as shared memory:
- Read
.agents/em-context.mdfirst if it exists - If a specific person is involved, also read
.agents/reports/[name].md - If
.agents/em-context.mddoes not exist, collect the minimum manager profile and create it before giving detailed advice - If a specific person is involved and
.agents/reports/[name].mddoes not exist, collect the minimum direct report profile and create it before giving detailed advice - If the conversation reveals durable new context, update the relevant file automatically
- Prefer additive updates over rewrites
- Do not overwrite existing context unless the user clearly corrected it
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 · 196 lines · 0 tokens per session scan A b598d5cd93ac
em-context is a skill published in the GitHub repository manager-dot-dev/manager-skills (109 stars, last pushed 3mo ago), licensed MIT. It adds 95 tokens to every session and 1,452 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.