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/samuelclay/newsblur/commit-allgit clone --depth 1 https://github.com/samuelclay/NewsBlurWhat 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 | $0.00010 | $0.00426 |
| Opus 5 | $0.00005 | $0.00213 |
| Sonnet 5 | $0.00002 | $0.00085 |
| Haiku 4.5 | $0.00001 | $0.00043 |
Grade A, and why
commit-all 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.
What it actually says
Context
- Current git status: !
git status - Current branch: !
git branch --show-current - Staged changes: !
git diff --staged --stat - Unstaged changes: !
git diff --stat - Full diff of all changes: !
git diff HEAD - Recent commits (for message style): !
git log --oneline -10
Your task
Analyze ALL uncommitted changes (staged and unstaged) and group them into logical, semantically related commits. Then create one commit per group.
Step 1: Analyze and group changes
Review every changed file in the diff above. Group them by logical purpose:
- Files that are part of the same feature or fix belong together
- Config changes related to a feature go with that feature
- Unrelated fixes, style changes, or independent modifications get their own commits
- Test files go with the code they test
Optionally present the proposed grouping, then proceed to committing.
Step 2: Commit each group
For each group (in logical order — foundational changes first):
- Reset the staging area:
git reset HEAD(if anything is staged) - Stage only the files for this group:
git add <specific-files> - Verify with
git diff --staged --stat - Commit with a HEREDOC message following the project conventions:
- Imperative mood, present tense
- Concise summary under 80 characters
- End with
Co-Authored-By: Claude Opus 4.6 <[email protected]>
Step 3: Confirm
Run git log --oneline -<N> (where N = number of commits created) and git status to show:
- All commits created (hash + message)
- Any remaining uncommitted files and why they were excluded
Do not push. Do not create a PR.
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 · 49 lines · 10 tokens per session scan A 52b6a9d9dd2d
commit-all is a command published in the GitHub repository samuelclay/NewsBlur (7,606 stars, last pushed yesterday), licensed MIT. It adds 10 tokens to every session and 426 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 commands, from other repositories
speckit.git.commit
Auto-commit changes after a Spec Kit command completes.
write-docs
아래 주제에 대한 VitePress 문서 페이지를 작성한다: $ARGUMENTS.
compound
현재 작업에서 재사용 패턴을 추출해 AGENTS.md·문서를 업데이트한다. 같은 종류의 버그·구현을 2회 이상 해결했거나 작업 종료 시 재사용 가치가 보일 때 사용. 일회성 작업에는 쓰지 않는다.
deep-research
해결이 어려운 구현·버그·설계 문제를 Fable 5.1로 깊게 분석한다. 한두 번 시도로 원인이 안 잡히거나 설계 트레이드오프 판단이 필요하거나 표면적 수정이 반복 실패할 때 사용. 단순·명확한 작업에는 쓰지 않는다.
release-mobilewright
Prepare a mobilewright release by updating CHANGELOG.md with the next patch version.
mobile-verify
Run automated verification loops with pass@k metrics for mobile testing. Executes tests multiple times to detect flakiness.