What is artifact-management?

Rules for maintaining project memory files, such as task specifications, development plans, architecture notes, known issues, and backlogs.

Use it to manage directory-specific AGENTS.md files and global project artifacts. It defines how task and plan files are archived and how architecture and issue records are maintained.

It clarifies which role may create or update each shared document and keeps long-term project information organized.

artifact-management — Skill by MatrixFounder

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.

agentmods

npx agentmods add skills/matrixfounder/agentic-development/artifact-management

Any agent

npx skills add MatrixFounder/Agentic-development --skill artifact-management

Clone the repo

git clone --depth 1 https://github.com/MatrixFounder/Agentic-development

Made for: Claude Code, Codex.

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,262 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00038	$0.01262
Opus 5	$0.00019	$0.00631
Sonnet 5	$0.00008	$0.00252
Haiku 4.5	$0.00004	$0.00126

Measured 2d ago against content hash 30e439c6f73a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

artifact-management 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.

.agent/skills/artifact-management/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Artifact Management

Local .AGENTS.md (Per-Directory)

Purpose: Distributed long-term memory for specific directories.
Location: In source-code directories covered by project memory policy (e.g., src/services/.AGENTS.md).
Single Writer: ONLY the Developer agent is allowed to create or update these files. All other agents (Analyst, Reviewer, etc.) must only READ them.

Format:

# Directory: src/services/

## Purpose
[Brief description of the directory's purpose]

## Files

### [filename.py]
**Classes/Functions:**
- `[ClassName]` — [Description]
  - `[method_name]` — [Description]

Global Artifacts

TASK.md: Technical Specification. Managed by Analyst. Archived to docs/tasks/task-NNN-slug.md.
PLAN.md: Development Plan. Managed by Planner. Rotated in lockstep with TASK.md to docs/plans/plan-NNN-slug.md (reuses the same ID/slug).
ARCHITECTURE.md: System Architecture. Managed by Architect. A LIVING document — updated in place, never per-task archived. Only restructured (split into docs/architectures/ section chunks + a short index) when it exceeds 1500 lines.
KNOWN_ISSUES.md: Known-issues ledger. A LIVING, hand-maintained thin index (one file per issue under docs/issues/) — updated in place, never per-task archived. Its format is defined in known-issues-format, not here (the frontmatter schema, prefix→category table, status/severity vocab, index-line format, and per-issue recipe live there — parallel to how ARCHITECTURE.md's structure lives in architecture-format-core). Create-if-absent: if the ledger is missing when you record an issue, first materialize it from known-issues-format's assets/templates/known_issues_md_template.md, then file the issue.
BACKLOG.md: Work-item ledger — enhancements, polish, and signals with no broken contract (defects go to KNOWN_ISSUES.md). Also a LIVING, hand-maintained thin index (one file per work-item under docs/backlog/), updated in place, never per-task archived, and human-ranked — no machine-imposed sort. Its format is defined in known-issues-format too (same skill, Registry B: type: work-item, WI-<n>, open/done/dropped, optional effort/value/source, index line after the  anchor). Create-if-absent from that skill's assets/templates/backlog_md_template.md — unless the project already tracks work under another name (docs/ROADMAP.md, an iteration backlog), in which case seat the anchor in that file rather than starting a second ledger.

Read the full file on GitHub · 80 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.

2d ago First seen · 80 lines · 38 tokens per session scan A 30e439c6f73a

Subscribe to this mod's changes

artifact-management is a skill published in the GitHub repository MatrixFounder/Agentic-development (5 stars, last pushed 20d ago), licensed Apache-2.0. It adds 38 tokens to every session and 1,262 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.

Memory and context Planning agentic ai-agents claude-code vdd

batch

Execute batch operations on multiple files in parallel. Automatically discovers files, splits into chunks, and processes with parallel worker agents. Use /batch followed by operation and file pattern.

QwenLM/qwen-code · 37 tokens

extension-creator

Create, scaffold, customize, validate, and locally test Qwen Code extensions. Use when the user wants a new Qwen Code extension, needs help choosing an extension template, wants to add QWEN.md context, commands, skills, agents, MCP servers, settings, hooks, channels, or LSP servers, or asks how to link and test an…

QwenLM/qwen-code · 96 tokens

notion

Notion API for creating and managing pages, databases, and blocks. Use when the user wants to create a Notion page, query a Notion database, update Notion properties, search Notion, add content to Notion, manage Notion blocks, or interact with Notion data sources and workspaces via the API.

elizaOS/eliza · 69 tokens

pr-feedback

Fetches PR review feedback and inline comments, categorizes them, and presents options to the user. Use when the user asks to get, read, address, or fix review comments on a pull request.

strands-agents/harness-sdk · 44 tokens

argent-native-profiler

Native profiling for CPU hotspots, UI hangs, memory issues. iOS via xctrace; Android via Perfetto. Use when diagnosing native-level performance issues.

software-mansion/argent · 37 tokens

argent-tv-interact

Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…

software-mansion/argent · 107 tokens