AC acpx-agent-playbook
Practical playbook for running agents through acpx in persistent sessions, especially when Claude, Codex, Pi, Gemini, OpenCode, or other ACP-compatible agents need reliable file creation, local installs, shell-based writes, or structured deliverables such as PPTX, reports, generated assets, and multi-step coding work. Use when work should be done via acpx rather than direct edits, or when prior acpx attempts failed because of quoting, session mode, permission policy, fs/write_text_file issues, sandbox boundaries, agent-specific CLI differences, or confusion about full-access vs true system privilege.
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 1
✓ No critical or high findings
Medium and low: 1
-
low Risky intent
intent-offensive-securitySKILL.md:62Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Do **not** assume `full-access` means sudo or root. It relaxes the ACP session; it does not guarantee system-level privilege escalation.
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 51/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 85Steps. 49 steps, 2 vague phrases
- 100Failures and branches. 8 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1774 tokens
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 607: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 49 items
- +4Has examples (7 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.