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 skills add kensaurus/cursor-kenji --skill docs-adrgit clone --depth 1 https://github.com/kensaurus/cursor-kenjiWrote 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/kensaurus/cursor-kenji/docs-adr)<a href="https://agentmods.dev/skills/kensaurus/cursor-kenji/docs-adr"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/docs-adr/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kensaurus/cursor-kenji/docs-adr"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/docs-adr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00050 | $0.01694 |
| Opus 5.5 | $0.00020 | $0.00678 |
| Sonnet 5.5 | $0.00010 | $0.00339 |
| Haiku 4.5 | $0.00005 | $0.00169 |
Grade A, and why
docs-adr 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 1mo 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
docs-adr — Decision memory the next session can load
Degree of freedom: MIXED — T1 is the priority. What to record
[HIGH freedom]; format, supersede-not-edit, and present-backfill-first
[LOW freedom — run exactly].
Install and maintain the repo's decision memory. Code shows what was decided; nothing shows why, or what was rejected — so every new agent session is free to "improve" its way back to an alternative you already ruled out. Re-litigated decisions are the slowest form of drift. An ADR makes the decision durable and its reversal deliberate.
This skill vs neighbors
| Skill | Owns |
|---|---|
| docs-adr (this) | Why we chose X; rejected alternatives; INDEX.md |
plan-docs-sync |
Docs vs what the code is — not why |
handoff |
Session state for the next chat — not permanent decisions |
docs-writer |
Tutorials / README prose |
enhance-arch-boundaries |
Mechanical layering; this records the model |
workflow-housekeep |
Periodic index / status sweep |
housekeep-backlog |
Parked-work register (BACKLOG.md), not decisions |
How to reason
- Observe — the decision, the rejected alternative, who already tried to reverse it
- Interpret — would a fresh agent "improve" back to the rejected option?
- Classify — ADR / not-an-ADR (linter already enforces, routine impl)
- Severity — load-bearing unusual choice first
Worked example
Observe: agent PR re-proposes Zustand; repo uses React context for session by choice; no ADR. Interpret: the rejection is oral memory — the next session will retry. Classify: ADR — stack choice with a rejected alternative. Write: "We use React context for session. Rejected Zustand: duplicate store vs server session." Present the backfill list before writing files.
Phase 0 — Set up the system (once per repo) [LOW freedom — INDEX.md + statuses]
docs/adr/NNNN-short-title.md, numbered sequentially, plusdocs/adr/INDEX.md— one line per ADR (NNNN | title | status | one-line decision). The index is the agent-facing surface: small enough to load every session.- Reference the index from agent rules: "Before proposing a change to
architecture, dependencies, conventions, or data models, read
docs/adr/INDEX.md; do not contradict an Accepted ADR without flagging it explicitly to the user." - Statuses: Proposed → Accepted → Superseded by NNNN / Deprecated. Never edit an Accepted ADR's decision — supersede it with a new one that links back. History is the point.
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.
- 1mo ago Changed · -16 tokens per session 0566ba31176f
- 1mo ago First seen · 169 lines · 66 tokens per session scan A 530fc9b7965e
docs-adr is a skill published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed 26d ago), licensed MIT. It adds 50 tokens to every session and 1,694 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
memory-awareness
Proactive memory usage for continuity across sessions. Use when a memory MCP is available — this skill governs when to automatically query and store memories, ensuring context persists between conversations. Triggers on task start, project context switch, architectural decision, complex bug resolution, and milestone…
update-memory-bank
Sync memory bank with repository state.
project-docs-management
A setup guide for creating a structured project knowledge base with AGENTS.md, an architecture document, and organized Markdown folders.
ui-design
Create distinctive, production-grade web interfaces with high design quality using Tailwind CSS. Use for building UI components, pages, dashboards, apps, and web applications. Generates crafted, polished code that avoids generic AI aesthetics.
code-review-codex
Final-gate code review via Codex CLI (codex-5.3, xhigh). Finds bugs, security issues, and regressions before commit. No edits — findings report only.
summarizer
Summarize a YouTube video or podcast episode and save the summary as a structured note in NotePlan under '3 Resources/Podcasts, YT/'. Use this skill whenever the user shares a YouTube link and wants it summarized, noted, or saved — or says things like 'summarize this', 'add this to my notes', 'save this podcast'…