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/microsoft/shadowfrog/shadow-frog-meditatenpx skills add microsoft/ShadowFrog --skill shadow-frog-meditategit clone --depth 1 https://github.com/microsoft/ShadowFrogWhat 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 | $0.00081 | $0.03349 |
| Opus 5 | $0.00041 | $0.01674 |
| Sonnet 5 | $0.00016 | $0.00670 |
| Haiku 4.5 | $0.00008 | $0.00335 |
Grade A, and why
shadow-frog-meditate 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 3d 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 — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ShadowFrog Meditate
Shadow hygiene — deduplicate, merge, and resolve conflicts across the
entire .shadow/ knowledge base. Prerequisite: .shadow/ exists with
discoveries.
Why Meditate?
Over time, shadows accumulate noise:
- Duplicates: the same insight written differently by different sessions
- Near-duplicates: one discovery is a subset of another
- Conflicts: two discoveries contradict each other (code may have changed, or one was wrong)
- Cross-scope duplicates: a per-file discovery and a
_cross/entry saying the same thing
This noise confuses downstream agents and dilutes signal. Meditate cleans it up.
Phase 1: Scan
Use parallel subagents to scan the shadow. Each subagent handles a batch of shadow files.
Scope Optimization
Not every file needs scanning. To reduce cost:
- Skip files with 0-1 discoveries — they can't have internal duplicates
- Focus on files modified since last meditate — check
_meta/state.jsonlast_update_atagainst file modification times - Always scan files with 5+ discoveries — highest duplicate risk
For the first meditate after a large dream run, most files will need scanning. For incremental meditation after small updates, this can reduce scope by 80%+.
Per-File Scan
For each per-file shadow (e.g., src/auth.py.md):
- Read all discoveries under each
## symbolheading - For each pair of discoveries under the same symbol, classify:
- Duplicate: same behavioral claim, different wording
- Near-duplicate: one discovery is a subset/refinement of the other
- Conflict: the two discoveries make contradicting claims
- Distinct: genuinely different insights — no action needed
- Record each finding as a structured action (see below)
Scan Output Format
Subagents must output findings as one JSON object per line so the orchestrator can auto-apply resolutions. This is critical for automation — prose recommendations require manual interpretation.
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.
- 3d ago First seen · 329 lines · 81 tokens per session scan A e3ee2df106bb
shadow-frog-meditate is a skill published in the GitHub repository microsoft/ShadowFrog (21 stars, last pushed 14d ago), licensed MIT. It adds 81 tokens to every session and 3,349 once invoked, about $0.0004 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.
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.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…