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.
npx skills add DeevsDeevs/agent-system --skill chain-systemgit clone --depth 1 https://github.com/DeevsDeevs/agent-systemWrote 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.
[](https://agentmods.dev/skills/deevsdeevs/agent-system/chain-system)<a href="https://agentmods.dev/skills/deevsdeevs/agent-system/chain-system"><img src="https://agentmods.dev/badge/skills/deevsdeevs/agent-system/chain-system/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.
<a href="https://agentmods.dev/skills/deevsdeevs/agent-system/chain-system"><img src="https://agentmods.dev/badge/skills/deevsdeevs/agent-system/chain-system.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00068 | $0.00778 |
| Opus 5.5 | $0.00027 | $0.00311 |
| Sonnet 5.5 | $0.00014 | $0.00156 |
| Haiku 4.5 | $0.00007 | $0.00078 |
Grade A, and why
chain-system 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 1mo 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.
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.
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:
- 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
- Create a slug (kebab-case) and a human readable title.
- Create the directory:
mkdir -p .claude/chains/<chain-name>. - Generate timestamp in local time:
date '+%Y-%m-%d-%H%M'. - Write the summary to:
.claude/chains/<chain-name>/<timestamp>-<slug>.md - 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:
- Find the most recent link:
ls .claude/chains/<chain-name>/*.md 2>/dev/null | sort -r | head -1
- If none, tell the user the chain does not exist and suggest
list. - Read the file fully and internalize it as working context.
- List the 5 most recent links:
ls .claude/chains/<chain-name>/*.md 2>/dev/null | sort -r | head -5
- Detect insufficiency and ask questions if needed:
- Missing context referenced by the link
- Ambiguous "Next Step"
- Stale link (>7 days old)
- Show the user: chain name, most recent link filename, short summary, next step, and the 5 most recent links.
- If any insufficiency flags exist, stop and clarify before proceeding.
What ships with it
5 files 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.
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.
- 1mo ago First seen · 84 lines · 68 tokens per session scan A 8dec0e83b302
chain-system is a skill published in the GitHub repository DeevsDeevs/agent-system (41 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 68 tokens to every session and 778 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
session-flow
Reorient in the current Claude Code session with an evidence-backed map of its goal, pivots, outcomes, current step, and open decisions.
wiki
LLM Wiki — persistent markdown knowledge base that compounds across sessions (Karpathy model).
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
deja-search
Search deja before re-deriving past work: when the user refers to earlier sessions or decisions, before debugging an error, and before implementing something that may already exist. It searches this machine's own history across every AI coding tool used on it, going back further than deja itself was installed.
deja-history
Search the user's past AI coding sessions. Holds what they already settled and never wrote into the repo (naming rules, banned or already-tried tools, required checks before merge, preferred values, who owns what). Use before your first edit in a task, before you call a change done or ready to merge, before you…
memory
Persistent, token-efficient project memory. When ON, maintains a .shob/memory/ folder of structured .md files so the full context of the project is NEVER lost across responses, sessions, or context compaction. Uses progressive disclosure — routes through a lightweight INDEX and loads only the files a task needs…