kioku: Skill for Claude Code

.agents/skills/kioku-project-workflow/SKILL.md

kioku-project-workflow is a skill for Claude Code, Codex from sandovaldavid/kioku. It costs 39 tokens per session (1,646 once invoked), scanned A, original, MIT.

A workflow guide for substantial projects managed through the Kioku MCP server. It covers starting, resuming, planning, implementing, reviewing, debugging, and documenting project work.

In plain words
What is it for?
Use it for major Kioku-managed development tasks, including loading project context, coordinating work, and recording documentation.
Why use it?
It helps an agent find the right project context and follow a deliberate repository-and-memory workflow before changing code or notes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is sandovaldavid/kioku's own configuration. It tells Claude Code and Codex how to work on kioku itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything kioku configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sandovaldavid/kioku. 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/sandovaldavid/kioku/main/.agents/skills/kioku-project-workflow/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sandovaldavid/kioku

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.

agentmods badge for kioku-project-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/sandovaldavid/kioku/kioku-project-workflow/github.svg)](https://agentmods.dev/skills/sandovaldavid/kioku/kioku-project-workflow)
Your own site
<a href="https://agentmods.dev/skills/sandovaldavid/kioku/kioku-project-workflow"><img src="https://agentmods.dev/badge/skills/sandovaldavid/kioku/kioku-project-workflow/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.

agentmods 80×15 button for kioku-project-workflow

Your own site · 80×15
<a href="https://agentmods.dev/skills/sandovaldavid/kioku/kioku-project-workflow"><img src="https://agentmods.dev/badge/skills/sandovaldavid/kioku/kioku-project-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,646 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00039 $0.01646
Opus 5 $0.00019 $0.00823
Sonnet 5 $0.00008 $0.00329
Haiku 4.5 $0.00004 $0.00165

Measured 10d ago against content hash 0f8fef03fe9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

kioku-project-workflow 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 10d 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.

.agents/skills/kioku-project-workflow/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kioku project workflow

Use this skill to turn a project request into a deliberate repository-and-vault workflow. Kioku provides project memory, guarded Markdown writes, sessions, and optional coordination. The client remains responsible for repository inspection, code changes, tests, Git operations, and external services.

Inputs

Extract:

  • project: the exact Kioku project identifier returned by list_projects or stored in the project MOC project: field.
  • task: the requested outcome, constraints, acceptance criteria, repository, and target branch when known.

Do not derive a vault path from owner/repository, a similarly named folder, or prior convention. When the identifier is missing or ambiguous, call list_projects, inspect the relevant MOC, and resolve the project before writing.

Workflow

1. Discover capabilities and load context

For project work:

  1. Confirm the active repository and target branch with the client's repository tools.
  2. Call get_server_capabilities when optional groups or coordination may be needed.
  3. Call get_project_context(project=...) before editing code or project notes.
  4. Read only relevant context, normally in this order:
    • project MOC and latest session handoff;
    • approved/current specs, active plans, and open bugs;
    • relevant ADRs, tickets, backlog items, and knowledge notes.
  5. Inspect the source repository's current code, tests, contracts, configuration, documentation, issues, and pull requests. Vault context is not a substitute for source evidence.

Treat approved specs as current durable requirements. Draft specs are in progress; superseded and discarded specs are historical and must not be silently treated as current instructions.

Respect .kioku/config.yml folder roles, exclusions, templates, and capability policy. Do not invent local paths, credentials, or unavailable capability groups.

2. Classify the request

Choose the smallest workflow that preserves useful context:

Request Default action
Explanation, lookup, or status Read/search only; no session or vault write
Feature/design needing durable behavior requirements Create or update a first-class spec; create an implementation plan from that spec when execution begins
Multi-step implementation with no durable design gap Start a session; create/update a plan when it helps execution
Bug investigation or fix Start a session; record a bug only when root cause and evidence are reusable
Architecture choice Read existing ADRs; record a proposed ADR before treating the decision as accepted
Reusable verified lesson Save project knowledge after validation
Deferred improvement Add a backlog item rather than expanding scope
Documentation synchronization Separate current public repository truth from private reasoning and handoff context

Read the full file on GitHub · 146 lines

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.

  1. 10d ago First seen · 146 lines · 39 tokens per session scan A 0f8fef03fe9e

Subscribe to this mod's changes

kioku-project-workflow is a skill published in the GitHub repository sandovaldavid/kioku (0 stars, last pushed 5d ago), licensed MIT. It adds 39 tokens to every session and 1,646 once invoked, about $0.0002 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.

Related

Other skills, from other repositories