A documentation-management procedure for software projects using files such as product specifications, architecture records, release notes, setup guides, and sprint plans. It defines how these documents are updated and organized.

Use it to update project documents, create or split stories, record decisions, write lessons or release notes, and run documentation checks.

It prevents code changes and project decisions from becoming disconnected from the documentation. It also sets rules for same-commit updates and recorded project history.

How Koniverse/Senti-MCP configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to Koniverse/Senti-MCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Koniverse/Senti-MCP/main/.agents/skills/koni-docs/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/Koniverse/Senti-MCP

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/koniverse/senti-mcp/koni-docs/github.svg)](https://agentmods.dev/skills/koniverse/senti-mcp/koni-docs)

Your own site

<a href="https://agentmods.dev/skills/koniverse/senti-mcp/koni-docs"><img src="https://agentmods.dev/badge/skills/koniverse/senti-mcp/koni-docs/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/koniverse/senti-mcp/koni-docs"><img src="https://agentmods.dev/badge/skills/koniverse/senti-mcp/koni-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 213 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,064 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00213	$0.05064
Opus 5	$0.00106	$0.02532
Sonnet 5	$0.00043	$0.01013
Haiku 4.5	$0.00021	$0.00506

Measured 8d ago against content hash 4916aa63ebce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

koni-docs 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 8d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/__tests__/fixtures/good/real-tool.py, scripts/__tests__/test-check-references.py, scripts/__tests__/test-coverage.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/koni-docs/SKILL.md · 272 lines

How it starts

The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.

koni-docs — Documentation Management

One rule above all others: every code-shipping commit updates docs in the SAME commit. Never defer documentation to a follow-up.

One carve-out, and only one: a commit's own SHA cannot be inside it. If a SHA is recorded at all, it is backfilled by a follow-up commit — never --amend-ed in, which orphans it (RULE-2).

0. Quick orientation — what lives where

docs/
├── README.md          ← doc hub + pre-commit checklist
├── SETUP.md           ← dev environment (clone → npm run dev)
├── BRIEF.md           ← product brief: executive summary, problem, solution, scope, vision
├── PRD.md             ← product spec: Epics / User Stories / Tasks
├── ARCHITECTURE.md    ← system architecture: tech stack, components, data, API, infra
├── CHANGELOG.md       ← full release history (every version)
├── CONTEXT.md         ← decision log (append-only, never rewrite)
├── LESSONS.md         ← recurring traps + patterns
├── design/            ← per-story design specs (US-X.Y-<slug>-design.md)
├── okr/               ← (optional) file-native quarterly OKR ledgers (YYYY-QN.md)
├── sprints/
│   ├── README.md      ← agile schema + workflow
│   ├── STATUS.md      ← AUTO-GENERATED kanban (never hand-edit)
│   ├── epics/         ← EPIC-N.md
│   ├── stories/       ← US-X.Y-<slug>.md (canonical task source)
│   ├── sprint-YYYY-WNN.md  ← active sprint
│   └── archive/       ← closed sprints
└── tests/
    ├── test-cases/    ← EPIC-N.md (epic-level scenarios: E2E + REG + SMK + matrix)
    │   └── README.md
    └── test-reports/  ← execution history (path owned by koni-qc test-organization)
        ├── EPIC-NN/<MMDDYYYY>/report.md  ← per-execution detail (auto; report-manual.md = manual)
        └── releases/  ← vX.Y.Z.md (per-release aggregate)

DEPLOY.md              ← production runbook (repo root)
VERSION                ← current semver string (repo root)
DESIGN.md              ← design system (repo root)
.env.example           ← env var template (repo root)

Read the full file on GitHub · 272 lines

Files

What ships with it

47 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.

Changes

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.

8d ago First seen · 272 lines · 213 tokens per session scan A 4916aa63ebce

Subscribe to this mod's changes

koni-docs is a skill published in the GitHub repository Koniverse/Senti-MCP (2 stars, last pushed 4d ago), licensed MIT. It adds 213 tokens to every session and 5,064 once invoked, about $0.0011 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 2026-08-31.

Writing and docs

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

Senti-MCP: Skill for Claude Code