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/refo/claude-dev-helpers/commitgit clone --depth 1 https://github.com/refo/claude-dev-helpersWhat 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 | $0.00011 | $0.00624 |
| Opus 5 | $0.00005 | $0.00312 |
| Sonnet 5 | $0.00002 | $0.00125 |
| Haiku 4.5 | $0.00001 | $0.00062 |
Grade B, and why
commit scanned grade B with 1 finding 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 yesterday.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Project helpers config (if present): !`cat .claude/helpers.json 2>/dev/null || echo "no helpers.json — fall back to inferring scope from changed paths and use a generic secrets blocklist"` How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit
Context
- Branch: !
git branch --show-current - Status: !
git status - Staged and unstaged diff: !
git diff HEAD - Recent commits (for style reference): !
git log --oneline -10 - Project helpers config (if present): !
cat .claude/helpers.json 2>/dev/null || echo "no helpers.json — fall back to inferring scope from changed paths and use a generic secrets blocklist"
Arguments
User provided: $ARGUMENTS
Instructions
Create a single git commit for the changes shown above.
Commit message format
Use Conventional Commits: type(scope): description
Types: feat, fix, refactor, chore, docs, style, test, perf, ci, build
Scope selection:
- If
helpers.jsondefinescommit.scopes, pick the most appropriate one from that list based on the changed paths. - Otherwise, infer a short scope from the dominant changed area (e.g. directory name, package name, top-level module).
- If changes span multiple scopes, omit the scope or use the dominant one.
Rules:
- Subject line under 72 characters, lowercase, no period.
- Use imperative mood ("add feature" not "added feature").
- Add a blank line + body only when the "why" isn't obvious from the subject.
- Match the style of recent commits shown above.
- If
helpers.jsondefinescommit.trailer, append it after a blank line. Otherwise, appendCo-Authored-By: Claude <[email protected]>.
Argument handling
- No arguments: auto-generate message from diff.
--amend: amend the previous commit instead of creating a new one.- Any other text: use it as the commit subject line (still add trailer).
Staging
- If there are unstaged changes and nothing is staged: stage all modified/new files with
git add -A. - If some files are already staged: commit only the staged files (do not add unstaged changes).
- Never stage files matching the project's secrets blocklist. Read
commit.secretsBlocklistfromhelpers.jsonif present. If not present, use this default:.env*,.env.*,credentials*,secrets*,*.key,*.pem,*.p12,*.pfx,id_rsa*,*.sqlite,*.sqlite3,*.db.
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.
- yesterday First seen · 59 lines · 11 tokens per session scan B 6e88117b8b74
commit is a command published in the GitHub repository refo/claude-dev-helpers (2 stars, last pushed 2mo ago), licensed MIT. It adds 11 tokens to every session and 624 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.