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 agentmods add commands/deevsdeevs/agent-system/chain-loadgit clone --depth 1 https://github.com/DeevsDeevs/agent-systemWhat 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 | $0.00000 | $0.00382 |
| Opus 5 | $0.00000 | $0.00191 |
| Sonnet 5 | $0.00000 | $0.00076 |
| Haiku 4.5 | $0.00000 | $0.00038 |
Grade A, and why
chain-load 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.
What it actually says
Loads the most recent chain link to continue work from a previous session.
Chain name: $ARGUMENTS
If no chain name provided, ask the user which chain to load (suggest using /chain-list).
Steps
- Check chain exists and find most recent link (by timestamp in filename):
ls .claude/chains/[chain-name]/*.md 2>/dev/null | sort -r | head -1
If no result, inform user chain doesn't exist and suggest /chain-list.
-
Read the file fully - this is your working context
-
List the 5 most recent links:
ls .claude/chains/[chain-name]/*.md 2>/dev/null | sort -r | head -5
-
Detect Insufficiency - check for gaps requiring user input:
- Missing Context: Link references files/decisions not captured. Ask: "Link references [X] - verify current state?"
- Ambiguous Next-Steps: "Next Step" is vague. Ask: "Next step unclear: [quote]. What specifically?"
- Stale Data: Link older than 7 days. Ask: "Link [N] days old. Project diverged?"
If ANY gap detected: STOP. Interview user. No interpolation or assumptions.
-
Show the user:
- Chain name and most recent link filename
- Brief summary (from Readable Summary if present)
- Next Step from loaded file
- Insufficiency flags with specific questions (if any)
- List of 5 most recent links
-
If gaps flagged, clarify before proceeding. Otherwise ask about loading additional links
Note: Fully internalize the loaded content - it's your working context. Only show the user a brief summary.
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 · 39 lines · 0 tokens per session scan A af07e0f23003
chain-load is a command published in the GitHub repository DeevsDeevs/agent-system (40 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 382 tokens. 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 commands, from other repositories
psm
/oh-my-claudecode:psm is a compatibility alias for /oh-my-claudecode:project-session-manager.
plan-review
The core plan review flow across Claude Code, Codex, and other supported agent hosts.
release
Ship a stable cmux release built by CI: bump version, update changelog, open a PR, merge, tag, then GitHub Actions builds, signs, and publishes.
refresh-compare-pages
Freshly research, add, and refresh marketing compare pages, then open a descriptive PR.
release
This compatibility command keeps /oh-my-claudecode:release available without loading the full release skill description in every Claude Code session.
step-research
Always research before proposing a fix. The Untether bug you're chasing is often a known upstream engine quirk, a previously-fixed regression, or a documented config gotcha.