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/commitgit 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 | $0.00009 | $0.00513 |
| Opus 5 | $0.00005 | $0.00257 |
| Sonnet 5 | $0.00002 | $0.00103 |
| Haiku 4.5 | $0.00001 | $0.00051 |
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.
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
Create a single git commit with only the changes relevant to this conversation session.
Step 1: Determine which files to stage
Analyze the conversation history and the diff above to identify which files were actively worked on during this session. Consider:
- Files you created, edited, or wrote during this conversation
- Files that are logically related to the work discussed
- Do NOT stage files with unrelated changes (pre-existing dirty state, editor configs, etc.)
If ALL changed files are clearly part of the current work, stage them all. If unsure about a file, leave it unstaged.
Step 2: Stage the relevant files
Use git add with specific file paths. Do NOT use git add -A or git add ..
If there are already-staged files that are NOT part of this session's work, unstage them with git reset HEAD <file>.
Step 3: Verify staged changes
Run git diff --staged --stat to confirm only the intended files are staged.
Step 4: Commit
Follow the commit message conventions from the recent commits above:
- Imperative mood, present tense ("Add...", "Fix...", "Rename...", "Enable...")
- Concise summary under 80 characters
- If non-trivial, add a blank line and brief body explaining the "why"
- End with
Co-Authored-By: Claude Opus 4.6 <[email protected]>
Use a HEREDOC:
git commit -m "$(cat <<'EOF'
<summary line>
Co-Authored-By: Claude Opus 4.6 <[email protected]>
EOF
)"
Step 5: Confirm
Run git status and report:
- The commit hash and message
- Which files were committed
- Which files remain unstaged (if any) 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.
- yesterday First seen · 65 lines · 9 tokens per session scan A 08af6ff594ae
commit is a command published in the GitHub repository samuelclay/NewsBlur (7,600 stars, last pushed 3d ago), licensed MIT. It adds 9 tokens to every session and 513 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
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.
qa
QA 전문가 — 테스트 기획 및 작성. 새 기능에 테스트가 필요하거나 기존 테스트의 신뢰성(Potemkin·Flaky)이 의심될 때 사용. 실제 기능·성능 검증 중심.
instrument
Generate a comprehensive instrumentation plan for a mobile codebase.
audit
Scan a codebase for existing observability instrumentation and identify gaps.
mobile-verify
Run automated verification loops with pass@k metrics for mobile testing. Executes tests multiple times to detect flakiness.
platform-info
Detect project type (Android/iOS/KMP), list platforms, show platform info, and delegate to appropriate commands.