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 skills add cintia09/CodeNook --skill config-mutatorgit clone --depth 1 https://github.com/cintia09/CodeNookWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cintia09/codenook/config-mutator)<a href="https://agentmods.dev/skills/cintia09/codenook/config-mutator"><img src="https://agentmods.dev/badge/skills/cintia09/codenook/config-mutator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cintia09/codenook/config-mutator"><img src="https://agentmods.dev/badge/skills/cintia09/codenook/config-mutator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00000 | $0.00603 |
| Opus 5.5 | $0.00000 | $0.00241 |
| Sonnet 5.5 | $0.00000 | $0.00121 |
| Haiku 4.5 | $0.00000 | $0.00060 |
Grade A, and why
config-mutator 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 2mo 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
config-mutator (builtin skill)
Role
Dispatched config writer. Updates a single config value at workspace or task scope, validates against schema, and appends a structured audit-log line. Implements implementation.md §M5.6.
CLI
mutate.sh --plugin <p> --path <dotted.path>
(--value <new> | --value-json <json>)
--reason <text> --actor <distiller|user|hitl>
--workspace <ws>
[--scope workspace|task --task <tid>]
--scope defaults to workspace. When --scope task is given,
--task is required.
--value parses its argument as JSON for type fidelity (so 5
round-trips as integer 5, true as boolean, "5" as the string
"5"); it falls back to a raw string when the argument is not
valid JSON (e.g. some-string, tier_balanced). Use --value-json
when you need an unambiguous JSON value and want a hard error on
parse failure.
Algorithm
-
Validate
--path: top segment must be in the §45 whitelist; reject leading_or..anywhere. -
Read current effective value via
config-resolve. If the new value matches → exit 0 with{"changed": false}and do not touch the audit log. -
For
scope=workspace: deep-set into<ws>/.codenook/config.yaml.plugins.<p>.overrides.<dotted.path>. -
For
scope=task: deep-set into<ws>/.codenook/tasks/<tid>/state.json.config_overrides.<dotted.path>. -
Append one JSON line to
<ws>/.codenook/history/config-changes.jsonl:{"ts":"...", "plugin":"...", "scope":"workspace|task", "task": "T-NNN" or null, "path":"...", "old": <prev>, "new": <new>, "actor":"distiller|user|hitl", "reason":"..."}
Invariants
- #44 router invariant — if
plugin == __router__andpathstarts withmodels.router, exit 1 (router model is invariant). - #45 whitelist — top-level segment of
pathmust be in{models, hitl, knowledge, concurrency, skills, memory, router, plugins, defaults, secrets}. actorenum is enforced; anything else → exit 2.
What ships with it
2 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.
- 2mo ago First seen · 62 lines · 0 tokens per session scan A 401bf98954a4
config-mutator is a skill published in the GitHub repository cintia09/CodeNook (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 603 tokens. 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.
config-mutator compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| config-mutatorcintia09/CodeNook | Skill | 5 | 1mo ago | MIT | A | 0 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 2d ago | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | 2d ago | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 315k | 5d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |