agentleFS
Sign inStart free
DeevsDeevsDeevsDeevs/agent-system/chain-system/SKILL.md

chain-system

Skill40 starsChanged 8 months agoApache-2.0View on GitHub

Create, list, and load multi-session chain links that capture work context for later continuation. Use when you want to save current progress, resume a project from a prior session, or inspect chain history. Triggers: chain link, chain load, chain list, save context, resume work, continue later, session handoff.

We split this skill into the rules it gives an agent

12 rules. About 0 are common, 5 are distinctive, and 7 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 7

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If the chain name is missing for link or load, ask the user for it.

    line 22
  2. Very specific:

    Default to .claude/chains to remain compatible with the existing Claude chain-system plugin.

    line 26
  3. Distinctive:

    Create a new chain link summarizing the current work.

    line 32
  4. Distinctive:

    Create a slug (kebab-case) and a human readable title.

    line 45
  5. Very specific:

    Create the directory: mkdir -p .claude/chains/<chain-name>.

    line 46
  6. Very specific:

    Write the summary to: .claude/chains/<chain-name>/<timestamp>-<slug>.md

    line 48
  7. Distinctive:

    Write only the summary (no analysis), then tell the user the file path and how to load it.

    line 50
  8. Very specific:

    Use the same file format each time so load can extract summary and next step reliably.

    line 52
  9. Very specific:

    If none, tell the user the chain does not exist and suggest list.

    line 61
  10. Distinctive:

    Read the file fully and internalize it as working context.

    line 62
  11. Distinctive:

    If any insufficiency flags exist, stop and clarify before proceeding.

    line 70
  12. Very specific:

    If no chains exist, suggest link to start one.

    line 83

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Chain System

Overview

Capture durable, structured summaries of work so a later session can resume without re-discovery. Provide three subcommands under one skill: link, load, and list.

Usage

Invoke with a subcommand:

$chain-system link <chain-name>
$chain-system load <chain-name>
$chain-system list

If the chain name is missing for link or load, ask the user for it.

Chain Root

Default to .claude/chains to remain compatible with the existing Claude chain-system plugin. If the user explicitly wants Codex-only storage, switch to .codex/chains and confirm.

Subcommands

link

Create a new chain link summarizing the current work.

Steps:

  1. Build a concise but complete summary using this structure:
    • Primary Request and Intent
    • Key Technical Concepts
    • Work Completed
    • Decisions and Rationale
    • Files and Code Changes (Created/Modified/Read)
    • Unresolved Issues and Blockers (only if any)
    • Pending Tasks
    • Current Work
    • Next Step
  2. Create a slug (kebab-case) and a human readable title.
  3. Create the directory: mkdir -p .claude/chains/<chain-name>.
  4. Generate timestamp in local time: date '+%Y-%m-%d-%H%M'.
  5. Write the summary to: .claude/chains/<chain-name>/<timestamp>-<slug>.md
  6. Write only the summary (no analysis), then tell the user the file path and how to load it.

Use the same file format each time so load can extract summary and next step reliably.

load

Load the most recent chain link for a named chain.

Steps:

  1. Find the most recent link:
    • ls .claude/chains/<chain-name>/*.md 2>/dev/null | sort -r | head -1
  2. If none, tell the user the chain does not exist and suggest list.
  3. Read the file fully and internalize it as working context.
  4. List the 5 most recent links:
    • ls .claude/chains/<chain-name>/*.md 2>/dev/null | sort -r | head -5
  5. Detect insufficiency and ask questions if needed:
    • Missing context referenced by the link
    • Ambiguous "Next Step"
    • Stale link (>7 days old)
  6. Show the user: chain name, most recent link filename, short summary, next step, and the 5 most recent links.
  7. If any insufficiency flags exist, stop and clarify before proceeding.

list

List all chains with counts and most recent link.

Steps:

  1. Check for chains:
    • ls -d .claude/chains/*/ 2>/dev/null
  2. For each chain, show:
    • chain name (directory)
    • link count (ls .claude/chains/<chain-name>/*.md 2>/dev/null | wc -l)
    • most recent link filename (ls .claude/chains/<chain-name>/*.md 2>/dev/null | sort -r | head -1)
  3. If no chains exist, suggest link to start one.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free