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/tacoda/keystone/keystone-bootstrapnpx skills add tacoda/keystone --skill keystone-bootstrapgit clone --depth 1 https://github.com/tacoda/keystoneWrote 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/tacoda/keystone/keystone-bootstrap)<a href="https://agentmods.dev/skills/tacoda/keystone/keystone-bootstrap"><img src="https://agentmods.dev/badge/skills/tacoda/keystone/keystone-bootstrap.svg" alt="Measured on agentmods" 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 | $0.00025 | $0.00709 |
| Opus 5 | $0.00013 | $0.00354 |
| Sonnet 5 | $0.00005 | $0.00142 |
| Haiku 4.5 | $0.00003 | $0.00071 |
Grade A, and why
keystone-bootstrap 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 4d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
keystone:bootstrap — make the charter specific to your codebase
The first thing to run after keystone init. Walks the repo, detects
the real stack, and replaces every template placeholder under
.charter/corpus/state/ with code-grounded values.
The canonical playbook is the bootstrap action at
.charter/actions/bootstrap.md. This skill is a thin
trigger that points the agent at it — open the action and execute its
activities in order.
Run
Open .charter/actions/bootstrap.md and execute every activity
listed under ## Activities. Every activity must land a real file
change before moving on; narration does not count.
A short summary of the work, copied from the action:
- Detect the stack (
package.json,go.mod,pyproject.toml, …). - Seed
corpus/state/CODEBASE_STATE.mdwith real tool commands + region map. - Scaffold
corpus/idioms/<stack>/+ pairedguides/idioms/<stack>/withglobs:derived from the region map. - Inventory
guides/computational/from.editorconfig, LSP config, formatter configs. - Classify every sensor under
sensors/as runnable or not for the selected adapter. - Build
corpus/state/GLOBS_INDEX.md— the reverse index from glob → guides. - Project rules to the agent's native surface (
.cursor/rules/,.claude/skills/, or the index-driven path for pointer-style adapters).
After every state-file write or new primitive, run keystone index so
.keystone/INDEX.json reflects the new shape. If skills, subagents,
or commands changed, run keystone project to regenerate .claude/.
When to trigger
- Immediately after
keystone init, before the first real task. - After a major stack change (new language, framework upgrade, monolith → services split) — re-bootstrap to refresh the region map and idiom seeds.
Completion check
Bootstrap is not done until:
grep -E '<[^>]+>' .charter/corpus/state/CODEBASE_STATE.mdreturns no template placeholders.last_reconciledinCODEBASE_STATE.mdis today's date.corpus/idioms/<stack>/andguides/idioms/<stack>/exist for each detected stack.- Every seeded idiom guide declares real
globs:. corpus/state/GLOBS_INDEX.mdlists at least one row per seeded guide (or is explicitly empty).
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.
- 4d ago First seen · 83 lines · 25 tokens per session scan A 210d6eb5d85e
keystone-bootstrap is a skill published in the GitHub repository tacoda/keystone (44 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 709 once invoked, about $0.0001 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
integrated-browser
Use this when working on the VS Code integrated browser ("browserView") to understand its architecture and mental model. Covers the embedded Chromium browser, its editor tab, navigation, overlay/layout, sessions, and agent browser tools under src/vs/platform/browserView and src/vs/workbench/contrib/browserView.
import-prom-rule
Bulk import of a Prometheus alert rule YAML file (create a whole set of rules at once). Dedicated to handling a remote URL or local YAML text, automatically parsing the three formats groups / a plain rules array / a single rule. ⚠️ Do not use this skill for single-rule creation — when the user describes a single alert…
pcbway
PCBWay PCB fabrication and assembly — turnkey/consigned assembly, design rules, ordering workflow. Alternative to JLCPCB for manufacturing. Use with KiCad. Use this skill when the user mentions PCBWay, needs turnkey assembly (PCBWay sources parts by MPN), has parts not available on LCSC, needs assembled boards with…
unifi-protect
How to manage UniFi Protect cameras and NVR — view cameras, smart detections, Find Anything detection search, recordings, snapshots, lights, sensors, Known Faces, license plates, and the Alarm Manager. Use this skill when the user mentions UniFi cameras, security cameras, NVR, recordings, motion detection, person…
tilelang-env-check
TileLang-Ascend 环境检查与配置验证技能。检查代码仓库完整性、编译安装状态、环境变量配置，并运行简单测试验证环境。发现问题会自动调用相关 skill 进行修复，并按依赖顺序重新执行后续步骤。触发关键词："环境检查"、"检查环境"、"验证环境"、"环境配置"、"环境搭建"、"env check"、"check environment"、"verify environment"、"setup environment"。.
KernelWiki
Use when the user asks about optimizing NVIDIA Blackwell (SM100, B200) or Hopper (SM90, H100) GPU kernels — tcgen05/TMEM/CLC/NVFP4/2-SM cooperative, warp specialization, FlashAttention-4, DeepGEMM, FlashMLA, MoE, grouped GEMM, CuTe-DSL/PTX/Triton on Blackwell, or wants concrete PR references from…