BB cc-codex-collaborate
Coordinate Claude Code and Codex in a milestone-based collaboration loop. Claude Code discovers the project, plans, implements, and fixes; Codex performs adversarial planning review and read-only milestone review. Working documents are stored under docs/cccc.
As a process B 69/100 · Nearly there — weak spots: result and completion, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
- 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-wallet-secretshooks/cccc-sensitive-op-guard.sh:10Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (detector / deny-list definition)SECRET_REGEX='(private key|seed phrase|mnemonic|wallet key|api[_-]?key|secret|password|token|keystore|id_rsa|id_ed25519|\.pem|\.key)'
detector
Files scanned: 63. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 7858 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 69/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70Failures and branches. 26 branches
- 70Execution cost. Instruction body is 7858 tokens
- 100Steps. 250 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 26 top-level sections: this looks like several domains in one skill
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
- -38 of 27 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 259: enough signal without eating the budget
- +4Structure: 50 headings
- +3Step-by-step instructions: 250 items
- +4Has examples (15 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 59.
External checks
ClawHub: suspicious
This looks like a real collaboration automation skill, but it needs Review because it can persist agent hooks, send broad project context to Codex, and rewrite workflow state in ways that may weaken safety pauses.
LLM: suspicious (high) · VirusTotal: · 29 May 2026