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 skills add ToruAI/toru-claude-agents --skill dev-finishgit clone --depth 1 https://github.com/ToruAI/toru-claude-agentsWrote 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/toruai/toru-claude-agents/dev-finish)<a href="https://agentmods.dev/skills/toruai/toru-claude-agents/dev-finish"><img src="https://agentmods.dev/badge/skills/toruai/toru-claude-agents/dev-finish/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/toruai/toru-claude-agents/dev-finish"><img src="https://agentmods.dev/badge/skills/toruai/toru-claude-agents/dev-finish.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 | $0.00024 | $0.02989 |
| Opus 5 | $0.00012 | $0.01494 |
| Sonnet 5 | $0.00005 | $0.00598 |
| Haiku 4.5 | $0.00002 | $0.00299 |
Grade A, and why
dev-finish scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 485 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev Finish - Quality Gate & Close
Complete a dev-cycle session: QA Gate → Code Review → Fix Issues → Commit → PR → Learn → Archive
Key principle: We ship quality. The project's own checks must exit 0 first, then Bob and Garry review before we close. Arlo joins when data/analytics are involved.
Agent Roles in Review
- Bob: Code quality, bugs, security, performance, tests
- Garry: Requirements match, architecture, completeness
- Arlo: Data logic, calculations, patterns, analytics accuracy (when applicable)
Flow
1. Find Active Session
ls ~/.claude/dev-cycles/active/ | grep "$(basename $(pwd))"
If no active session:
- "No active dev-cycle found for this project. Nothing to finish."
- Exit
If found:
- Read session file
- Show summary of what was done
2. Generate Diff for Review
Save the full diff to a file for thorough review:
# Create review directory if needed
mkdir -p ~/.claude/dev-cycles/reviews
# Get project and branch info
PROJECT=$(basename $(pwd))
BRANCH=$(git branch --show-current)
TIMESTAMP=$(date +%Y%m%d-%H%M%S)
# Save full diff to file
git diff main...HEAD > ~/.claude/dev-cycles/reviews/${PROJECT}--${BRANCH}--${TIMESTAMP}.diff
# Also save stat summary
git diff main...HEAD --stat > ~/.claude/dev-cycles/reviews/${PROJECT}--${BRANCH}--${TIMESTAMP}.stat
Present summary to the user:
- Files changed
- Lines added/removed
- Diff saved to:
{path}
3. QA Gate (objective, runs first)
Run the checks before any opinion. Use the dev-qa skill: the project's own tests, linter, type checker and build. Pass = exit code 0. Not "looks fine" — zero.
If anything exits non-zero:
QA gate failed:
- tests: exit 1 (2 failures)
- lint: exit 0
- build: exit 0
Options:
1. Fix now (Bob fixes, then the gate runs again)
2. Fix manually, then run /dev-finish again
3. Abandon this session
This skill does not offer to commit while the gate is red. If the user wants to ship a red build anyway, they can commit by hand — that is their call to make, not this skill's to offer.
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.
- 9d ago First seen · 485 lines · 24 tokens per session scan A 1e223a4e1805
dev-finish is a skill published in the GitHub repository ToruAI/toru-claude-agents (15 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 2,989 once invoked, about $0.0001 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 skills, from other repositories
close-task-commit-push-pr
Close the active backlog task (detected from branch name), commit all changes, push to remote, and open a pull request. Use when the user says "close task and ship it", "close task commit push pr", or invokes /close-task-commit-push-pr.
artifact-metadata
Manage artifact metadata, versioning, ownership, and review history across the SDLC lifecycle.
cross-repo-cache
Check if cross-repo coordinator results can be reused, avoiding redundant Sonnet agent launches. Compares peer repo git hashes against stored hashes from last coordinator run. Triggers on: entering Phase 1.4.1, checking cross-repo cache, before discovering peers. Returns CROSSREPOCACHEHIT with cached status or…
aiwg-delivery-pr
AIWG-specific delivery pull request workflow; explicit alias for aiwg-pr, not a generic repository PR guide.
release
Prepare a version release — bump version files, commit, and tag. Just run /release with no arguments.
release-init
Detect project type and generate a tailored project-level /release skill. Run once per project to set up releasing.