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/princeton-ddss/blackfish/prgit clone --depth 1 https://github.com/princeton-ddss/blackfishWrote 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/commands/princeton-ddss/blackfish/pr)<a href="https://agentmods.dev/commands/princeton-ddss/blackfish/pr"><img src="https://agentmods.dev/badge/commands/princeton-ddss/blackfish/pr.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00741 |
| Opus 5 | $0.00000 | $0.00370 |
| Sonnet 5 | $0.00000 | $0.00148 |
| Haiku 4.5 | $0.00000 | $0.00074 |
Grade A, and why
pr 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 3d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a pull request for the current branch.
$ARGUMENTS
Step 1: Validate branch state
git branch --show-current
git status
Ensure we're not on main/dev and there are commits to push.
Step 2: Run pre-PR checks
For Python backend (if lib/ files changed):
cd lib && uv run just lint
cd lib && uv run just test
cd lib && uv run just coverage
For frontend (if web/ files changed):
cd web && npm run lint
cd web && npm test
If any checks fail, report the issues and stop. Do not create the PR.
Step 3: Analyze changes for PR content
git log --oneline main..HEAD
git diff main...HEAD --stat
Step 4: Create the PR
Push the branch and create the PR using gh:
git push -u origin $(git branch --show-current)
gh pr create --title "..." --body "..."
Use this PR body format:
-
Summary (2-3 bullet points)
-
Test plan (verification steps)
Do not add a Claude Code attribution footer.
If there's a linked issue, include "Closes #N" in the PR body.
Step 5: Update project status (if linked issue exists)
If the branch name starts with an issue number (e.g., 123-feature-name) or the PR body contains "Closes #N":
- Check if
.claude/projects.jsonexists. If not, skip this step. - Read the projects array. If multiple projects, ask user which one (or try to find the issue in each).
- Find the issue's item ID in the project:
gh project item-list <project_number> --owner <owner> --format json | jq -r '.items[] | select(.content.number == <issue-number>) | .id' - Move the issue to "In review" status using IDs from the config:
gh project item-edit --id "<item-id>" --project-id "<project_id>" --field-id "<fields.status.id>" --single-select-option-id "<fields.status.options['In review']>"
If the issue is not in any project, no linked issue exists, or no projects config exists, skip this step.
Step 6: Wait for and triage Claude bot review
A Claude bot runs an automated code review on every PR opened. It posts its
review as a PR comment from the claude user. It takes a few minutes, so poll
for that comment rather than checking once (poll every ~60s, up to ~10
minutes). If no bot review appears, say so and stop.
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.
- 3d ago First seen · 95 lines · 0 tokens per session scan A 035170c82256
pr is a command published in the GitHub repository princeton-ddss/blackfish (24 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 741 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 2026-09-01.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
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.