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 mshadmanrahman/pm-pilot --skill shepherd-triagegit clone --depth 1 https://github.com/mshadmanrahman/pm-pilotWrote 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/mshadmanrahman/pm-pilot/shepherd-triage)<a href="https://agentmods.dev/skills/mshadmanrahman/pm-pilot/shepherd-triage"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/pm-pilot/shepherd-triage/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/mshadmanrahman/pm-pilot/shepherd-triage"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/pm-pilot/shepherd-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.02390 |
| Opus 5 | $0.00021 | $0.01195 |
| Sonnet 5 | $0.00008 | $0.00478 |
| Haiku 4.5 | $0.00004 | $0.00239 |
Grade A, and why
shepherd-triage 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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/shepherd-triage — Mass Reproducibility Check
Launch parallel agents to check whether old bugs still reproduce on the live site. This is the core Bug Shepherd workflow: turning a stale backlog into a prioritized, verified list.
Audience: PMs who need to clean a backlog without reading code.
Arguments
{count}(optional): Number of bugs to triage. Default: 30. Max: 60.
Workflow
1. Load Configuration
Read .claude/triage.config.yaml. If it does not exist, run the first-run setup
in /shepherd-sync step 1 to create it from the bundled template, then continue.
Read from it:
project.live_url— where to reproducereproduction.parallel_agents— how many agents to launch (default: 5)reproduction.bugs_per_agent— bugs per agent (default: 6)reproduction.triage_order— "priority" (default) or "oldest"reproduction.viewports,reproduction.timeout_per_bug,reproduction.max_screenshots_per_bug: cost and time limits passed to each agentsafety.*— all safety rules
2. Auto-Sync Backlog
If .claude/backlog-live.md is older than 24 hours, run /shepherd-sync first.
3. Select Bugs to Triage
From backlog-live.md, select untriaged bugs (those not marked "Triaged"):
- If
triage_orderis "priority" (default): sort by priority first (Highest > High > Medium > Low > Lowest), then by created date (oldest first) within each priority - If
triage_orderis "oldest": sort by created date (oldest first), ignoring priority - Skip bugs already in triage logs
- Respect
{count}parameter - Report: "Selected {count} bugs for triage (priorities: {P1}xHighest, {P2}xHigh, {P3}xMedium, {P4}xLow; oldest: {date}, newest: {date})"
4. Pre-Triage Safety Filter
Before launching agents, apply safety filters:
For each selected bug, check:
- Recent activity: If comments or updates within
safety.recent_activity_days, move to "SKIP — Active" list - Active assignee: If
safety.skip_assignedis true and bug has an assignee, move to "SKIP — Assigned" list - Never-auto-cancel category: If bug summary/description matches any
safety.never_auto_cancelkeyword, flag as "ALWAYS HUMAN REVIEW"
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · +43 lines e6f35b17934f
- 10d ago First seen · 209 lines · 42 tokens per session scan A 335f96e33e6a
shepherd-triage is a skill published in the GitHub repository mshadmanrahman/pm-pilot (20 stars, last pushed 4d ago), licensed MIT. It adds 42 tokens to every session and 2,390 once invoked, about $0.0002 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
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
browser-debugging
Chrome DevTools MCP ile browser debugging. Console, network, performance, DOM analizi.
hive.browser-automation
Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…
hive.linkedin-automation
Read before automating LinkedIn with browser tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Types CSP that silently drops innerHTML, Lexical composer, native beforeunload dialogs that hang the bridge, and aggressive spam filters — each has bitten us at least once. Verified flows for profile…
hive.x-automation
Read before automating X / Twitter with browser tools. Verified flows for post, reply, delete, search-and-engage, plus the Draft.js compose quirks that silently disable the send button. Includes the daily-reply and job-market-reply playbooks. Requires hive.browser-automation for the underlying screenshot + coordinate…
hive.slack-notifications-setup
Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…