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 commands/thedecipherist/claude-code-mastery-project-starter-kit/set-project-profile-defaultgit clone --depth 1 https://github.com/TheDecipherist/claude-code-mastery-project-starter-kitWrote 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/commands/thedecipherist/claude-code-mastery-project-starter-kit/set-project-profile-default)<a href="https://agentmods.dev/commands/thedecipherist/claude-code-mastery-project-starter-kit/set-project-profile-default"><img src="https://agentmods.dev/badge/commands/thedecipherist/claude-code-mastery-project-starter-kit/set-project-profile-default.svg" alt="Measured on agentmods" 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 | $0.00008 | $0.00850 |
| Opus 5 | $0.00004 | $0.00425 |
| Sonnet 5 | $0.00002 | $0.00170 |
| Haiku 4.5 | $0.00001 | $0.00085 |
Grade A, and why
set-project-profile-default 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 5d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set Project Profile Default
Set which profile /new-project uses by default when no profile is specified.
Arguments: $ARGUMENTS
Usage
/set-project-profile-default go → sets default_profile = go
/set-project-profile-default clean → sets default_profile = clean
/set-project-profile-default default → sets default_profile = default
/set-project-profile-default python-api → sets default_profile = python-api
/set-project-profile-default mongo next tailwind docker
→ creates/updates [user-default] profile with those settings
→ sets default_profile = user-default
/set-project-profile-default (no args)
→ shows current default, asks what to change
Steps
1. Read the config file
Read claude-mastery-project.conf from the project root. If not found, check ~/.claude/claude-mastery-project.conf.
Extract:
- All
[section]names (these are the available profiles) - Current
default_profilevalue from[global](if set)
2. Parse arguments
$ARGUMENTS can be:
A) No arguments — show current state and ask:
- Display the current
default_profilevalue (or "not set" if absent) - List all available profiles with a one-line summary of each
- Ask via AskUserQuestion: "Which profile should be the default?"
- Options: list all profile section names from the conf file
- After selection, proceed to Step 3
B) Single argument matching an existing [section] name (e.g., go, clean, default, api, vue, python-api):
- Proceed to Step 3 with that profile name
C) Multiple arguments (e.g., mongo next tailwind docker):
- Parse as shorthand options using the same parser as
/new-project:- Languages:
node,go,python - Frameworks:
vite,react,next,vue,nuxt,svelte,sveltekit,angular,astro,fastify,express,hono,gin,chi,echo,fiber,stdlib,fastapi,django,flask - Database:
mongo,postgres,mysql,mssql,sqlite - Hosting:
dokploy,vercel,static - Package managers:
pnpm,npm,bun,pip,uv,poetry - Options:
seo,ssr,tailwind,prisma,docker,ci,multiregion - Analytics:
rybbit - MCP:
playwright,context7,rulecatch
- Languages:
- Create or update a
[user-default]section in the conf file with the parsed settings - Set
default_profile = user-defaultin[global] - Proceed to Step 4 (confirmation)
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.
- 5d ago First seen · 80 lines · 8 tokens per session scan A 534e041dd94a
set-project-profile-default is a command published in the GitHub repository TheDecipherist/claude-code-mastery-project-starter-kit (337 stars, last pushed 2mo ago), licensed MIT. It adds 8 tokens to every session and 850 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.