Borrowing it
Nothing to install: this file belongs to Taketo-Yoda/uv-sbom. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Taketo-Yoda/uv-sbom/develop/.claude/skills/sync-config/SKILL.mdgit clone --depth 1 https://github.com/Taketo-Yoda/uv-sbomWrote 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/taketo-yoda/uv-sbom/sync-config)<a href="https://agentmods.dev/skills/taketo-yoda/uv-sbom/sync-config"><img src="https://agentmods.dev/badge/skills/taketo-yoda/uv-sbom/sync-config/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/taketo-yoda/uv-sbom/sync-config"><img src="https://agentmods.dev/badge/skills/taketo-yoda/uv-sbom/sync-config.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 | $0.00015 | $0.01241 |
| Opus 5.5 | $0.00006 | $0.00496 |
| Sonnet 5.5 | $0.00003 | $0.00248 |
| Haiku 4.5 | $0.00002 | $0.00124 |
Grade A, and why
sync-config 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 25d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sync-config - CLI-Config Sync Skill
Audits src/cli.rs against src/config.rs and src/main.rs to detect CLI options that are not exposed through the config file layer, and guides fixing any gaps found.
Trigger Examples
/sync-config- "Check that all CLI options are reflected in the config file"
- "Verify CLI options are synced with config"
Background: The Five-Location Rule
Every CLI option intended to be user-configurable must appear in five places:
| Location | What to add |
|---|---|
src/config.rs — ConfigFile struct |
pub <field>: Option<T> |
src/config.rs — CONFIG_TEMPLATE |
Commented-out YAML entry with description |
src/main.rs — MergedConfig struct |
<field>: T |
src/main.rs — merge_config() |
CLI > config > default priority logic |
src/main.rs — request builder |
Pass merged value to SbomRequest |
Reference Implementation: check_cve
Use check_cve as the canonical pattern when adding a new boolean flag:
src/config.rs — ConfigFile:
pub check_cve: Option<bool>,
src/config.rs — CONFIG_TEMPLATE:
# Enable CVE vulnerability checking
# check_cve: false
src/main.rs — MergedConfig:
check_cve: bool,
src/main.rs — merge_config():
// check_cve: CLI flag || config value
let check_cve = args.check_cve || config.check_cve.unwrap_or(false);
src/main.rs — request builder:
.check_cve(merged.check_cve)
Workflow
Step 1: Audit — Extract CLI Options
Read src/cli.rs and list all pub fields in the Args struct.
Exclude from audit (infrastructure, not user-configurable features):
config(-c/--config) — selects the config file itselfinit(--init) — generates the config templatepath(-p) — project pathoutput(-o) — output file path
Step 2: Audit — Check ConfigFile Coverage
Read src/config.rs and list all fields in the ConfigFile struct (excluding unknown_fields).
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.
- 25d ago Changed · +1 lines e46dd68e9633
- 1mo ago First seen · 156 lines · 15 tokens per session scan A f7cc9c711517
sync-config is a skill published in the GitHub repository Taketo-Yoda/uv-sbom (6 stars, last pushed yesterday), licensed MIT. It adds 15 tokens to every session and 1,241 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-04.
Other skills, from other repositories
review-test-stubs
Review the test stubs for coverage, scope, vacuous-assertion freedom, finding-grounded scope, and happy-path completeness against the interview and the modeled schema — not for code quality.
review-implementation
Gate the implementation against its contract for correctness, quality, drift, and green tests.
code-review
Perform a structured code review of changes, checking for correctness, style, tests, and potential issues.
code-review
Code review assistance with linting, style checking, and best practices.
splitting-oversized-modules
Split an oversized Python module (a thousand-plus-line logic.py, models.py, api.py, or its test file) into a package of one module per concern, mechanically and provably without changing behavior. Use on a request to split / break up / decompose a god module or move functions out of one, once a human has agreed to…
red-team-review
Unified adversarial review, two modes. Strategic Matrix v4.3 (MTA-004) for arguments/plans/decisions: Priors → Rubric → Adversarial Lenses → SWOT/TOWS → MCDA → Blind Spot/Kill Switch → Summary. Deliverable Audit for built artefacts (assignments, reports, code outputs): isolated fresh-context hunt against the brief…