Instructions for a shared developer memory system that stores useful facts, decisions, errors, and project context across conversations. It separates general knowledge from information tied to one project.

Use it to decide what to save, where to store it, how to retrieve it, and when to record completed work or lessons learned.

It helps coding work continue across sessions without relying only on the current chat history.

dev-wiki — Skill for Claude Code and Codex by oleg494/coding-kit

Install

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.

Any agent

npx skills add oleg494/coding-kit --skill dev-wiki

Clone the repo

git clone --depth 1 https://github.com/oleg494/coding-kit

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/oleg494/coding-kit/dev-wiki/github.svg)](https://agentmods.dev/skills/oleg494/coding-kit/dev-wiki)

Your own site

<a href="https://agentmods.dev/skills/oleg494/coding-kit/dev-wiki"><img src="https://agentmods.dev/badge/skills/oleg494/coding-kit/dev-wiki/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/oleg494/coding-kit/dev-wiki"><img src="https://agentmods.dev/badge/skills/oleg494/coding-kit/dev-wiki.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 129 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,723 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	$0.00129	$0.01723
Opus 5.5	$0.00052	$0.00689
Sonnet 5.5	$0.00026	$0.00345
Haiku 4.5	$0.00013	$0.00172

Measured 2d ago against content hash 725d04878bbd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dev-wiki 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 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.

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/dev-wiki/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dev Wiki — cross-chat developer memory

Memory helper: knowledge base of decisions, bugs, patterns, architectural decisions. Memory lives in ~/.memory/ (global + per-project hierarchy; env MEMORY_ROOT overrides).

Boundary rule

Knowledge	Where	Index
Portable (patterns, lessons, decisions)	`~/.memory/Wiki/<type>/`	`python ~/.memory/db-tools/build.py`
Project-specific (status, configs, context)	`WORK/<project>/docs/`	`python ~/.memory/db-tools/build.py -r <root> -o ~/.memory/db/<name>.db`

Knowledge lives/dies with the project → project; portable across projects → global Wiki.

Save reflex (bounded by task effect boundary)

Side-effect boundary: read-only or review-only tasks produce NO memory writes unless explicitly requested by the user.
On every finished mutation task / made decision / closed bug — 10-second check: would a future session need this? Yes → save. No → skip (noise-free is deliberate).
Conclusions → findings.py add; portable patterns → Wiki; realizations by trigger below. Any saved verify_cmd is a proposed check, not standing authorization.
A handoff or continuity record is compact: what command was run, on what state/scope/environment, what result, and what invalidates it (change, failure, unresolved concern). Reuse it for an unchanged checked state; do not build a new tracking subsystem around it.

Record types (global Wiki)

Type	Folder	When
`reference`	`~/.memory/Wiki/reference/`	Fact, documentation, knowledge
`howto`	`~/.memory/Wiki/howto/`	Instruction, guide
`error`	`~/.memory/Wiki/errors/`	Bug, incident, lesson learned
`decision`	`~/.memory/Wiki/decisions/`	ADR, architectural decision
`idea`	`~/.memory/Wiki/ideas/`	Idea

Workflow — save (global)

Determine the type → folder in ~/.memory/Wiki/.

Create file ~/.memory/Wiki/<type>/<slug>.md with frontmatter:

---
type: reference
title: "Title"
description: "About what"
date: 2026-08-15
tags: [category, topic]
---

Update ~/.memory/Wiki/index.md.
Append to ~/.memory/Wiki/log.md.
python ~/.memory/db-tools/build.py
python ~/.memory/db-tools/lint_wiki.py
Important conclusion → python ~/.memory/db-tools/findings.py add "topic" --text "conclusion" --source path --project <slug> --importance <high|normal|low>

Read the full file on GitHub · 112 lines

Files

What ships with it

1 file 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.

evals/evals.json 1.6 KB

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.

2d ago Changed 725d04878bbd
9d ago Changed · +9 tokens per session e52ec16349fc
11d ago Changed · +4 lines d5b529964e50
25d ago Changed f735c02354f0
26d ago Changed f5e8fe64afee
1mo ago Changed · +3 lines 9cc875280dfd
1mo ago Changed 25854e798943
1mo ago Changed · +27 lines e71e3b63b773
1mo ago Changed 63e1568d67cc
1mo ago First seen · 78 lines · 120 tokens per session scan A 77fc8ce185db

Subscribe to this mod's changes

dev-wiki is a skill published in the GitHub repository oleg494/coding-kit (3 stars, last pushed 2d ago), licensed MIT. It adds 129 tokens to every session and 1,723 once invoked, about $0.0005 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 2026-08-31.

Claude Code Memory and context agent-skills ai-agents evals gemini-cli hermes

mnemosyne

Persistent cross-session memory via Mnemosyne — store, recall, and consolidate facts, preferences, and context.

mnemosyne-oss/mnemosyne · 22 tokens

factory-init

Use when onboarding a brownfield repo onto ADLC end-to-end, or running the recurring PDR↔ADR↔ChDR↔code alignment sweep (--refresh).

tikalk/adlc-team-skills · 38 tokens

neo4j-agent-memory-skill

Authoritative reference for the neo4j-agent-memory Python package — a graph-native memory system for AI agents built on Neo4j — and for the hosted service (NAMS) at memory.neo4jlabs.com. Use this skill whenever the user mentions neo4j-agent-memory, agent memory with Neo4j, context graphs, the POLE+O model…

neo4j-contrib/neo4j-skills · 223 tokens

change-boot

Use when past-change rationale matters (refactoring unfamiliar code, revert or hotfix analysis, issue-linked commit archaeology, session authors git changes with human-authored messages) — injects the published ChDR index (docs/adlc/memory/chdr.md, legacy .adlc/memory/chdr.md fallback) as session context; pairs…

tikalk/adlc-team-skills · 102 tokens

team-levelup

Use when a session ends to extract CDRs, score confidence, batch review, and publish accepted CDRs to team-ai-directives. Auto-triggers on sessionend event. Also invoked from team-boot's Class Boots catalog for CDR descriptor matches.

tikalk/adlc-team-skills · 57 tokens

curator

Use when ingesting memory into the wiki, running wikicurator.py (run/report/validate/lint/search), or linting wiki structure.

moonlight-lupin/agent-skills · 32 tokens