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/jpesewang/solo-dev-workflow/commitgit clone --depth 1 https://github.com/jpeseWang/solo-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 | $0.00000 | $0.00828 |
| Opus 5 | $0.00000 | $0.00414 |
| Sonnet 5 | $0.00000 | $0.00166 |
| Haiku 4.5 | $0.00000 | $0.00083 |
Grade A, and why
commit 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 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.
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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit
Quality-gate the diff, auto-fix safe issues, and write a Conventional Commit.
A focused pipeline: understand the change, hold it to the four quality dimensions, fix the safe stuff, then commit with a clean message. No ceremony — no ticket lookup, no metrics.
Step 1 — Analyze the change
git status
git diff --stat
Read every changed file (staged + unstaged) so you understand the change, not just the lines.
If nothing is staged, stage the relevant files (git add -p mindset — only what belongs in
this commit). If the diff mixes two unrelated concerns, offer to split it into two commits.
Step 2 — Quality gate (4 dimensions)
Check the diff against the bar in AGENTS.md → Code quality bar:
| Dimension | Look for |
|---|---|
| Correctness | null safety, error handling, edge cases, exhaustive cases, no placeholder/debug logging |
| Design | clear names, short functions, no magic numbers, no dead code |
| Security | no hardcoded secrets, no logged credentials, validated input |
| Efficiency | no duplicated logic, no reinvented stdlib, no obvious perf traps |
Report what you found, grouped by dimension. Be concrete (file:line).
Step 3 — Auto-fix the safe issues
Fix in priority order Correctness → Design → Security → Efficiency. Only fix what is genuinely wrong and behavior-preserving. Leave anything judgment-heavy or risky for the developer — list those instead of touching them. If a fix would change >50% of a file, ask first. Re-stage after fixing.
Step 4 — Write the commit message
Conventional Commits: type(scope): subject
SUBJECT="feat(export): add CSV export to the reports page" # example
Validate before committing — all must pass:
- Prefix: one of
feat|fix|refactor|perf|test|docs|chore|style|build|ci, optional(scope). - Length: subject ≤ 72 chars.
- Mood: imperative —
add, notadded/adds/adding. - No trailing period.
- Body: add 1–3 lines explaining why when the subject doesn't make it obvious. Wrap a bug fix's body with what broke and how this fixes it.
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 · 93 lines · 0 tokens per session scan A 8d7a86f880e3
commit is a command published in the GitHub repository jpeseWang/solo-dev-workflow (2 stars, last pushed 11d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 828 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.
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.