agentmods.dev

threadbase-workflow

A workflow for setting up Threadbase and maintaining shared project memory in a repository. Threadbase stores human-readable decisions, requirements, changes, and issues in .ai files.

In plain words
What is it for?
Use it to initialize Threadbase, read project rules, generate or refresh context.md, and record decisions or implementation notes without storing secrets.
Why use it?
It helps coding agents recover project context between sessions and keeps the generated context file based on the repository's recorded memory.

Skill for Claude CodeCodex

4 2mo ago A scan 27 tokens original MIT
View the source file ani3198/threadbase
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/ani3198/threadbase/threadbase-workflow
Any agent
npx skills add ani3198/threadbase --skill threadbase-workflow
Clone the repo
git clone --depth 1 https://github.com/ani3198/threadbase

Made for: Claude Code, Codex.

Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 559 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 $0.00027 $0.00559
Opus 5 $0.00014 $0.00280
Sonnet 5 $0.00005 $0.00112
Haiku 4.5 $0.00003 $0.00056

Measured yesterday against content hash 2558e1dca42d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

threadbase-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 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.

plugins/threadbase-codex/skills/threadbase-workflow/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Threadbase Workflow

Use this skill when:

  • the user wants to set up Threadbase in the current repository
  • the repository already contains .ai/ Threadbase files
  • .ai/generated/context.md is missing, empty, or stale
  • you need to record decisions, changes, requirements, or issues in shared repo memory

Core Model

  • Treat .ai/memory/* as the source of truth.
  • Treat .ai/generated/context.md as derived output.
  • Keep memory human-readable and markdown-first.
  • Never store secrets, credentials, or tokens in Threadbase files.

Setup

  1. Work from the actual repository root or the agent workspace root for the project.
  2. If Threadbase is not initialized yet, prefer:
threadbase init
  1. If threadbase is not available on PATH, fall back to:
npx threadbase init
  1. If the user wants the generated files to stay local and untracked, use:
threadbase init --local

First Session

  1. Read .ai/rules.md.
  2. Read .ai/generated/context.md.
  3. If .ai/generated/context.md is missing or empty:
    • read .ai/prompts/generate_context.md
    • inspect the repository directly
    • generate the first .ai/generated/context.md from scratch
    • include YAML frontmatter with generated_at and source_file_count

If memory files already exist under .ai/memory/*, use them as the authoritative input when generating context.

During Work

  • Read .ai/generated/context.md before meaningful implementation changes.
  • If the context looks stale, regenerate it from .ai/memory/*.
  • Follow any additional project rules found in AGENTS.md and .ai/rules.md.

After Work

Record meaningful updates in one or more of:

  • .ai/memory/decisions/
  • .ai/memory/changes/
  • .ai/memory/requirements/
  • .ai/memory/issues/

For new memory entries:

  • Use one markdown file per item.
  • Prefer filenames like YYYYMMDD-HHMM-short-slug.md.
  • Include frontmatter with:
    • id
    • type
    • created_at
    • summary
  • Include body sections:
    • ## Context
    • ## Details

Read the full file on GitHub · 84 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 · 84 lines · 27 tokens per session scan A 2558e1dca42d

Subscribe to this mod's changes

threadbase-workflow is a skill published in the GitHub repository ani3198/threadbase (4 stars, last pushed 2mo ago), licensed MIT. It adds 27 tokens to every session and 559 once invoked, about $0.0001 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 contextPlanningProductivity
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