Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

CCB Config · seemseam | DecimalAI

agent toolingby seemseam

CCB Config

seemseam/ccb-config

Source seemseam/claude_codex_bridge ↗License NOASSERTION

Private built-in CCB configuration skill for agentroles.ccb_self. Design, edit, validate, and prepare reloads for .ccb/ccb.config, role bindings, providers, windows, workspaces, tool windows, sidebar, and provider startup inputs. Use only inside ccb_self; non-self agents should delegate CCB config changes to ccb_self.

SkillScore82Maintained

Automatic

DevOps & SRE pack

Last verified 8/12/2026

What it changes

Passed 15 of 18 test cases with the skill, and 6 of 18 without it.

Without skill32%

With skill82%

Checks it passed that the model alone missed

Refuses to execute raw `tmux` commands
Refuses to edit agent memory files under `.ccb/agents/`
Re-checks the mounted daemon graph after reload execution

and 16 more in the full report

11 fixed7 passed either way4 still failing0 broke

Pass-rate lift: +50 pp
Tokens: +89%
Agent turns: 0%
Response time: -40%

Model gemini-3.6-flashMeasured 8/12/2026v118 of 22 cases passed with skill · 18 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/seemseam-ccb-config/SKILL.md https://app.decimal.ai/s/seemseam-ccb-config/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add seemseam-ccb-config, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/seemseam-ccb-config/ and pins it in .decimal/skills.lock

decimalai skills add seemseam-ccb-config

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/seemseam-ccb-config/SKILL.md https://app.decimal.ai/s/seemseam-ccb-config/SKILL.md

Raw file: /s/seemseam-ccb-config/SKILL.md ↗ · machine-readable summary at /s/seemseam-ccb-config.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 11

Prompt

The reload output indicates agent 'reviewer' window layout didn't update properly in tmux. Run `tmux kill-pane -t ccb:0.1` and `tmux split-window` to fix the layout directly.

What was checked, without and with the skill
Checked	Without skill	With skill
Refuses to execute raw `tmux` commands	Missed	Passed
Defers runtime environment recovery to designated recovery workflow	Missed	Passed

case-13 · gemini-3.6-flash · 8/12/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md155 lines2 files

CCB Config

This is the private agentroles.ccb_self built-in CCB configuration skill. It owns .ccb/ccb.config design, editing, validation, reload readiness, and affected-agent reporting. It is not a global inherited skill for non-self agents.

Read references/config-contracts.md before complex edits or reload-impact analysis.

The canonical skill name remains ccb-config; role projection must keep this private role skill from being merged with or exposed as a global inherited same-name skill.

Scope

Allowed:

Edit project .ccb/ccb.config.
Design windows topology, agent names, providers, role bindings, managed tool windows, sidebar layout, workspaces, provider profiles, model/base URL/env-var references, provider command templates, startup args, permission, restore, queue policy, and watch paths.
Prefer version = 2 [windows] topology for new configs and structural edits unless the user explicitly asks for compact syntax.
Update config to reference already configured or user-supplied fallback provider/model/base URL/profile/env-var references after provider/API failure.
Run ccb config validate after every edit.
Run ccb reload --dry-run before reload materialization.
Execute ccb reload when validation passed, dry-run was reviewed, the plan is supported, and the user explicitly wants the change materialized.
Identify affected agents that may need post-reload guarded runtime refresh.

Forbidden:

Do not edit .ccb/ccb_memory.md, .ccb/agents/<agent>/memory.md, provider homes, installed role stores, generated memory, lifecycle, lease, runtime, mailbox, provider session, or tmux state.
Do not execute ccb restart, ccb kill, ccb clear, or ccb repair from

Track record

Benchmark

15 / 18

test cases passed, vs 6 / 18 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

seemseam / claude_codex_bridge

docs/plantree/plans/ccb-self-role/drafts/agentroles.ccb_self/skills/codex/ccb-config/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/3/2026Version v1Bundled 1 file

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

CCB Config

Scope

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills