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 skills/mshadmanrahman/pm-pilot/shepherd-syncnpx skills add mshadmanrahman/pm-pilot --skill shepherd-syncgit 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-sync)<a href="https://agentmods.dev/skills/mshadmanrahman/pm-pilot/shepherd-sync"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/pm-pilot/shepherd-sync.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 5.1 | $0.00035 | $0.00825 |
| Opus 5 | $0.00017 | $0.00413 |
| Sonnet 5 | $0.00007 | $0.00165 |
| Haiku 4.5 | $0.00003 | $0.00082 |
Grade A, and why
shepherd-sync 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 6d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/shepherd-sync — Backlog Synchronization
Pull all open bugs from your tracker into a local backlog file for offline triage.
Workflow
1. Load Configuration
Read .claude/triage.config.yaml to get tracker type, project key, and team settings.
If config file is missing:
"Config not found. Run the Bug Shepherd installer or create .claude/triage.config.yaml manually."
"See: https://github.com/YOUR_USERNAME/bug-shepherd#configuration"
2. Detect Tracker and Load Adapter
Based on project.tracker in config, load the matching adapter bundled with this skill in references/:
jira: Readreferences/jira.mdfor Jira-specific query patternslinear: Readreferences/linear.mdfor Linear-specific patternsgithub-issues: Readreferences/github-issues.mdfor GitHub Issues patterns
3. Pull Open Bugs
Execute the tracker-specific query to fetch ALL open bugs. Handle pagination.
For Jira (via Atlassian MCP):
- Use JQL:
project = {tracker_project} AND issuetype = Bug AND status NOT IN (Done, Cancelled) ORDER BY created ASC - Paginate: fetch up to 100 per page, continue with
created > {last_date}until no more results
For Linear (via Linear MCP):
- Query: open issues with label "bug" in the configured team
- Paginate using cursor
For GitHub Issues (via gh CLI):
- Query:
gh issue list --repo {repo} --label bug --state open --limit 500 --json number,title,state,labels,createdAt,assignees,body
4. Detect Current Sprint (if applicable)
For Jira: Query sprint in openSprints() to find the active sprint name and ID.
For Linear: Get current cycle.
For GitHub: Skip (no sprint concept).
Store sprint info for later use by /shepherd-triage.
5. Write Local Backlog
Write results to .claude/backlog-live.md:
# Bug Backlog — {project.name}
> Last synced: {ISO 8601 UTC timestamp}
> Sprint: {sprint_name} (ID: {sprint_id})
> Total open bugs: {count}
| Key | Status | Priority | Created | Assignee | Summary | Triaged |
|-----|--------|----------|---------|----------|---------|---------|
| {key} | {status} | {priority} | {date} | {assignee} | {summary} | {yes/no} |
What ships with it
3 files 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.
- 6d ago First seen · 94 lines · 35 tokens per session scan A 459212c34f2b
shepherd-sync is a skill published in the GitHub repository mshadmanrahman/pm-pilot (19 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 825 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
work-pipeline
Triggers the WORK-PIPELINE when a user request starts with a [] tag (e.g., [new-feature], [bugfix], [WORK start]). Use this skill whenever you detect a [] tag at the beginning of a user message.
feature-spec
Creates a complete product feature specification with acceptance criteria, scope, dependencies, and risks. Delegates to the Prometeo (PM) agent.
sdd-pipeline
파이프라인 에이전트(specifier, planner, scheduler, builder, verifier, committer)가 참조하는 규칙/스키마 문서 모음.
gmgn-dev-score
Decide whether a token creator's NEXT launch is safe to buy. Scores a dev address 0-100 on two separate axes — CONDUCT (will he dump on you at open) and POWER (has he ever actually built anything big) — from his full launch history and every trade he made in his own coins, then returns a buy / don't-buy call with a…
decided-import
Reformat ONE existing document (a decision, requirement, design, roadmap, or prompt) into ONE valid RAC (requirements-as-code) artifact, with a mandatory human-review step before any file is written and decided validate as the deterministic close. Use when a user wants to add or import a single existing decision or…
orch
AI agent orchestrator — manage teams of AI agents that work on your codebase in parallel. Use when the user wants to: run multiple agents, coordinate AI work, deploy agent teams, manage tasks/goals/agents, check orchestrator status, or mentions 'orch', 'orchestry', 'agents team', 'agent orchestration'.