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 agentmods add skills/tandnguyendev/dev-workflow/confignpx skills add tandnguyendev/dev-workflow --skill configgit clone --depth 1 https://github.com/tandnguyendev/dev-workflowWhat 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 | $0.00047 | $0.00816 |
| Opus 5 | $0.00023 | $0.00408 |
| Sonnet 5 | $0.00009 | $0.00163 |
| Haiku 4.5 | $0.00005 | $0.00082 |
Grade A, and why
config scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Report — and optionally change — how this project has configured the plugin.
The CLI is python3 "${CLAUDE_SKILL_DIR}/../../hooks/config.py" <cmd> (this resolves
to the plugin's hooks/config.py). It imports the guards themselves rather than
restating their defaults, so its report cannot drift from the hooks that are actually
running. Never answer this from memory or by reading the JSON files yourself: the
whole point is the gap between what a file SAYS and what the guards DO, and only the
CLI computes that.
Showing
Run exactly:
python3 "${CLAUDE_SKILL_DIR}/../../hooks/config.py" show
Present the output as a short table per section. Two things carry the value here, so do not flatten them away:
- The
PROBLEMSblock, if there is one — lead with it. Every guard falls back to its defaults when a config file will not parse, and says nothing; a!line means the project believes it configured something that is not happening. Quote the line and say plainly what is running instead. - The source column.
default/file/env <VAR>/file, IGNORED. That last one is the interesting case: the key was written, the guard read it, and the value is the default anyway — a wrong type, or a regex that will not compile.
If nothing is overridden and there are no problems, say so in one line rather than reprinting a wall of defaults: the project is on stock settings.
Setting
Only when the user asks for a change. Run:
python3 "${CLAUDE_SKILL_DIR}/../../hooks/config.py" set <key> <value>
Keys: comment-guard.enabled, comment-guard.density.floor,
comment-guard.density.min_ratio, test-guard.enabled, test-guard.checks.fakes,
test-guard.checks.assertions, test-guard.max_empty_args, models.<agent>.
Values: on / off, a number, a model alias (opus, sonnet, haiku, fable,
inherit) or a claude-* id, or default to drop the key.
The file is a diff against the defaults, so a value equal to its default is removed rather than written — that is intended, not a failure. The command refuses to write over a file it cannot parse; when it does, tell the user to fix or delete that file rather than trying to repair it yourself.
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.
- 2d ago First seen · 70 lines · 47 tokens per session scan A b74927f7874c
config is a skill published in the GitHub repository tandnguyendev/dev-workflow (2 stars, last pushed 8d ago), licensed MIT. It adds 47 tokens to every session and 816 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…