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/daaain/claude-code-log/foldyardnpx skills add daaain/claude-code-log --skill foldyardgit clone --depth 1 https://github.com/daaain/claude-code-logWhat 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 | $0.00100 | $0.01253 |
| Opus 5 | $0.00050 | $0.00626 |
| Sonnet 5 | $0.00020 | $0.00251 |
| Haiku 4.5 | $0.00010 | $0.00125 |
Grade A, and why
foldyard 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working in (and on) a foldyard dev box
Foldyard runs this project inside a rootless VM that mounts only this repo. You are almost certainly in the box — a container in that VM — and the person you're working with is on the host (their Mac). That split explains nearly everything below.
Check where you are: fy mode prints the posture and says which side it's reading from.
fy verify proves the boundary (it exits non-zero if any of it is false).
The four facts that will save you the most time
- You cannot push. No credential to the git remote reaches the box, by design. Read and commit locally; the human pushes. Don't try to work around it — there is nothing to find.
- You hold no real secrets, and can't grant yourself any. Posture state lives in the host's
home, outside the mount.
fy modeshows posture anywhere; setting it is host-only. - Your egress goes through the host's proxy and may be allow-listed or walled. A blocked host is a decision, not a bug — ask; don't route around it.
- The engine socket you have is real and bounded to this VM.
docker/podmancommands work and act on the live dev stack — including anything a test suite's mocks let slip.
Ask the tool, don't guess
Foldyard is introspectable, and its own output is always current — prefer it over any summary (including this one):
| question | command |
|---|---|
| what can this environment do right now? | fy mode (posture), fy state (desired vs observed) |
| what's broken / missing? | fy doctor — one line per check, each with its fix |
| is the isolation intact? | fy verify |
| what does this verb do? | fy --help, fy <verb> --help |
| the manual, offline, by topic | fy docs — then fy docs <topic> |
| what does the config let the host do? | fy config widenings |
fy docs serves this install's documentation, so it can't drift from the code you're running.
Start with fy docs quickstart, fy docs modes, fy docs networking, fy docs security; the
ADRs (fy docs adr-0001 …) carry the reasoning behind each design decision.
What ships with it
3 files 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.
- 2d ago First seen · 85 lines · 100 tokens per session scan A 0f662918c6ad
foldyard is a skill published in the GitHub repository daaain/claude-code-log (1,201 stars, last pushed 2d ago), licensed MIT. It adds 100 tokens to every session and 1,253 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.