filing-knowledge

A set of instructions for saving important answers, decisions, and temporary solutions as memory notes in a project’s .neatcode/memory directory.

In plain words
What is it for?
Use it after complex codebase analysis, important design decisions, or temporary stub implementations that should be documented.
Why use it?
It helps future coding-agent sessions recover useful context instead of deriving the same information again.

Skill for Claude CodeCodex

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/hitmandark07/neatcodeai/filing-knowledge
Any agent
npx skills add HITMANdark07/neatcodeai --skill filing-knowledge
Clone the repo
git clone --depth 1 https://github.com/HITMANdark07/neatcodeai

Made for: Claude Code, Codex.

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,548 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.

ModelPer sessionOnce invoked
Fable 5 $0.00057 $0.01548
Opus 5 $0.00028 $0.00774
Sonnet 5 $0.00011 $0.00310
Haiku 4.5 $0.00006 $0.00155

Measured yesterday against content hash f631be0e9862, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

filing-knowledge 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 yesterday.

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.

packages/cli/templates/skills/filing-knowledge/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Filing Knowledge

Overview

Every session that derives a non-trivial structural answer should leave behind a note. The next session — yours, a teammate's, a fresh agent in two months — should look up the answer in .neatcode/memory/ instead of re-running the same five graph queries.

This skill writes Markdown files to .neatcode/memory/<slug>.md. It does not call any neatcode MCP tool — it consumes the result of prior tool calls (typically from exploring-codebase) and persists it.

Trigger

Activate when, in the current turn, ANY of the following is true:

  1. The answer required more than two graph queries. If you called query_graph, trace_flow, or find_node three or more times to compose the answer, the next session shouldn't repeat that work.
  2. The answer involved interpretation across multiple files. Reading three files and synthesizing the relationship between them is exactly the kind of thing that compounds — write it down.
  3. The answer surfaced tribal knowledge. Anything along the lines of "ah, the reason this is shaped this way is..." that wasn't already documented in REPO_OVERVIEW.md, decisions/, or memory/.
  4. You shipped a placeholder, stub, or simplification during autonomous work. Examples: // TODO: real auth wired here, dev-user assumes all scopes, caching disabled until X is decided, magic constant 100 — pick the real number once telemetry exists. The next session needs to know what's pretending to work and what's load-bearing — file the placeholder, not just leave it in code.
  5. You made a load-bearing architectural choice not specified in the prompt. "I picked X over Y because Z" — write it down before the reasoning evaporates. This is most common during autonomous, multi-task runs where the agent makes 5-10 small judgment calls per phase that compound.

If none of these apply, skip. Trivial one-shot answers don't need notes.

The first three triggers cover answering a question. The last two cover autonomous work — file under the same skill since the destination (.neatcode/memory/) is the same. The agent doesn't need permission from the user to surface a filing proposal in autonomous flows; just propose, then continue.

Read the full file on GitHub · 108 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. yesterday First seen · 108 lines · 57 tokens per session scan A f631be0e9862

Subscribe to this mod's changes

filing-knowledge is a skill published in the GitHub repository HITMANdark07/neatcodeai (0 stars, last pushed 3mo ago), licensed MIT. It adds 57 tokens to every session and 1,548 once invoked, about $0.0003 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

systematic-debugging

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

obra/superpowers · 21 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

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 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