Write config
Tokenmaxxing Gateway for Claude Code
npx -y skills add zapgun-ai/clawback --skill write-configAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Generate or refresh the canonical CLAWBACK.md config. The front matter is built from the live DEFAULTS export in src/config.js (so it can never drift as options are added), with the only forced deviations being the two a LAN-reachable bind needs — host=0.0.0.0 and tls=true. adminToken is left as a null placeholder for you to set (it no longer mints one); a real existing token, or an explicit CLAWBACK_CANONICAL_TOKEN, is PRESERVED, and a token's value is NEVER printed (only presence and length). With no args it writes BOTH ./CLAWBACK.md and the global ~/.config/clawback/CLAWBACK.md. Use to (re)create a canonical config, or after adding an option or changing a default.
SKILL.md
2.6 KB, 505 tokens by cl100k_base, as published. Nobody here has run it
clawback canonical config writer
Run .skills/write-config/scripts/write_canonical_config.mjs from the project
root. It writes a canonical CLAWBACK.md: every option at its DEFAULT value
(generated from the live DEFAULTS in src/config.js, so it never drifts as
options change), except the two a LAN bind needs set — host=0.0.0.0 and
tls=true (it leaves adminToken as a null placeholder for you to set) —
followed by the documentation body in
canonical_config_body.md (in this skill's assets/ directory).
# write BOTH ./CLAWBACK.md and the global ~/.config/clawback/CLAWBACK.md:
node .skills/write-config/scripts/write_canonical_config.mjs
# write specific target(s):
node .skills/write-config/scripts/write_canonical_config.mjs ./CLAWBACK.md
# inject a real token instead of the null placeholder:
CLAWBACK_CANONICAL_TOKEN=… node .skills/write-config/scripts/write_canonical_config.mjs
adminToken handling (secret-safe)
The adminToken fronts live Anthropic credentials, so the script never mints
one and never prints a token's value. It resolves ONE shared value in this
order and writes it to every target so they agree:
CLAWBACK_CANONICAL_TOKENfrom the environment, if set;- a real existing token preserved from the first target that already has one
(a
null/ empty / placeholder token does NOT count — it is overwritten); - otherwise
null— a placeholder you must fill in.
With host: 0.0.0.0, the proxy refuses to bind until adminToken is set, so a
forgotten placeholder fails loud instead of exposing a guessable secret. Output
reports only presence, length, and origin — never a token's value.
Files written
- With no args:
./CLAWBACK.mdand${XDG_CONFIG_HOME:-$HOME/.config}/clawback/CLAWBACK.md. - Each is written
0600(owner-only; it holds a secret), enforced even when the file already existed.
Confirm the result parsed and merged with the verify-config skill.
What ships with it: 2 files
14.4 KB alongside SKILL.md, 1 of them executable
assets/
- canonical_config_body.md10.0 KB
scripts/
- write_canonical_config.mjsruns4.4 KB