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/hariharapanigrahy/layerkit/layerkit-author-processornpx skills add hariharapanigrahy/layerkit --skill layerkit-author-processorgit clone --depth 1 https://github.com/hariharapanigrahy/layerkitWhat 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 | $0.00021 | $0.00398 |
| Opus 5 | $0.00010 | $0.00199 |
| Sonnet 5 | $0.00004 | $0.00080 |
| Haiku 4.5 | $0.00002 | $0.00040 |
Grade A, and why
layerkit-author-processor scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. Identify the transform requirement from vendor docs/OpenAPI/curl and existing client mapper code. What it actually says
layerkit-author-processor
Use this skill when a vendor contract requires normalization, hashing, formatting, date conversion, object shaping, or other deterministic helper logic in the client package.
These helpers are client-owned source code. They are not Layerkit runtime processors.
Protocol
- Identify the transform requirement from vendor docs/OpenAPI/curl and existing client mapper code.
- Search for an existing helper before adding one.
- Prefer updating an existing helper or mapper method.
- Add a new helper only when no existing function can be changed cleanly.
- For any new helper, state what it replaces. If it replaces nothing, justify why it must exist.
- Add or update tests that prove the transform against cited examples.
- Validate any map/proposal artifact only if the client uses one:
layerkit proposal validate ./proposal.json
layerkit map validate ./map.json
Citation Rules
- Cite the vendor/customer rule for every non-obvious transform.
- Excerpts must cover the rule, such as hashing order, casing, phone format, timestamp unit, or nested object shape.
- If docs are silent, do not invent SHA variants, phone formats, timezone assumptions, or fallback defaults.
Forbidden
- Network, credentials, or AI calls inside transform helpers.
- Double-hashing or re-normalizing without evidence.
- Adding a parallel helper when an existing mapper/helper should be changed.
- Creating Layerkit processor proposal artifacts as a substitute for editing source.
Success Criteria
- Transform source code lives in the client package path.
- Existing code was updated or stale code was removed before adding a helper.
- Tests cover vendor examples or cited schema rules.
- Any remaining datalayer gap is a precise TODO in source and handoff.
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 · 46 lines · 21 tokens per session scan A 23a8c4c53edb
layerkit-author-processor is a skill published in the GitHub repository hariharapanigrahy/layerkit (8 stars, last pushed 25d ago), licensed MIT. It adds 21 tokens to every session and 398 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
bcc-plan-spar
BCC align+lock+review PLAN.md for one slice (no product code). Slash: /bcc-plan-spar · chat: bcc:plan-spar · "lock PLAN" · spar the plan. Args: rounds=N (auto-review cap), review=self|subagent|cli|auto|off. Grill until clear enough (no default Q&A quota). Hand off to bcc-clean-cut after human APPROVE.
bcc-throughline
BCC global progress cockpit (plans.md/progress.md/findings.md). Slash: /bcc-throughline · chat: bcc:throughline · "where are we" · reprioritize · resume after /clear. Not for coding or full PLAN grill.
bcc-breaking-coding-chaos
BCC main skill: dual-loop coding workflow (throughline → plan-spar → clean-cut) or quick status+next. Slash: /bcc-breaking-coding-chaos · chat: bcc:breaking-coding-chaos · "run BCC" · "BCC status" · "what next BCC". Needs a real idea (1:1 implement). Args: goal text, or status. May pass plan-spar review budget as…
chinese-git-workflow
适配国内 Git 平台和团队习惯的工作流规范——Gitee、Coding、极狐 GitLab 全覆盖.
chinese-commit-conventions
中文 Git 提交规范 — 适配国内团队的 commit message 规范和 changelog 自动化.
systematic-debugging
Skill "systematic-debugging" from Leodorareluctant259/superpowers-zh, covering 系统化调试, 概述, 铁律, 何时使用 and 四个阶段.