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 skills/conn-castle/agent-layer/auto-skill-loopnpx skills add conn-castle/agent-layer --skill auto-skill-loopgit clone --depth 1 https://github.com/conn-castle/agent-layerWhat 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 | $0.00017 | $0.00730 |
| Opus 5 | $0.00009 | $0.00365 |
| Sonnet 5 | $0.00003 | $0.00146 |
| Haiku 4.5 | $0.00002 | $0.00073 |
Grade A, and why
auto-skill-loop 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.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
auto-skill-loop
Inputs
Required:
- a
modematchingreferences/modes/<mode>.md merge_authorization: standing authorization to merge under the gate belowoperator,planner, one or moreplan_reviewers,implementer,code_reviewer,pr_worker, androte_workerdispatch targets
Optional:
loop_context: additional context for the orchestrator onlyplanner_context: additional context included only in step 1ship_pr_context: additional context included only in step 2operator_context: additional context included only inoperatordispatches
Every input must be explicitly named in the skill invocation. Do not infer an unnamed input from unstructured text or from another input.
Rules
- Use
/dispatch-agentfor every dispatch. - Act as the orchestrator. Delegate all work.
- Build each dispatch prompt only from its specified prompt template.
- When compacting, retain the original user inputs and this skill verbatim in addition to what you would normally retain.
Acting on the User's Behalf
This loop must run without human intervention. Each iteration is intended to result
in a merged PR. For each loop that requires human input, dispatch operator in
a fresh session. Use dispatch_continue for multiple invocations within a
single loop. The first prompt should include the complete contents of
references/human-guidance.md, followed by operator_context if provided, then
the item requiring human input with all provided details verbatim.
If the operator determines that real human intervention is required, save the
work to an appropriate remote branch for future handling, then check out the
primary branch. Continue with another loop iteration. Do not block the loop
waiting for human input.
Loop
- Dispatch
plannerwith skillimplement. Use the following as its prompt:
<complete contents of references/modes/<mode>.md>
<planner_context, if provided>
implementer: <implementer>
plan_reviewers: <plan_reviewers>
code_reviewer: <code_reviewer>
Return a self-contained `<implementation_input>` that states the actual task,
request, or spec you implemented and includes paths to plan artifacts if used.
This context will preserve the intended scope during later review.
What ships with it
7 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.
- 2d ago First seen · 96 lines · 17 tokens per session scan A b546457fc2fc
auto-skill-loop is a skill published in the GitHub repository conn-castle/agent-layer (10 stars, last pushed 3d ago), licensed MIT. It adds 17 tokens to every session and 730 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.
Other skills, from other repositories
openspec-explore
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
openspec-apply-change
Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
openspec-archive-change
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
openspec-propose
Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.
openspec-sync-specs
Sync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change.
openspec-update-change
Update an OpenSpec change by revising its existing planning artifacts and keeping them coherent with one another. Use when the user wants to revise a change's plan, fold new decisions into it, or reconcile its artifacts after an edit. Never edits code.