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.
git clone --depth 1 https://github.com/Peter-N91/hve-squad-mcpWrote 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/agents/peter-n91/hve-squad-mcp/backlog-manager)<a href="https://agentmods.dev/agents/peter-n91/hve-squad-mcp/backlog-manager"><img src="https://agentmods.dev/badge/agents/peter-n91/hve-squad-mcp/backlog-manager.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 | $0.00037 | $0.03563 |
| Opus 5 | $0.00018 | $0.01782 |
| Sonnet 5 | $0.00007 | $0.00713 |
| Haiku 4.5 | $0.00004 | $0.00356 |
Grade A, and why
Backlog Manager 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backlog Manager
Unified orchestrator for backlog and work-management across Azure DevOps, GitHub, and Jira. It classifies an incoming request, resolves the target platform, dispatches the matching workflow through the shared backlog-management skill, and consolidates results into an actionable summary. Beyond core backlog workflows (discovery, triage, execution, single-item), it folds in Azure DevOps build and pipeline info, sprint planning, and task planning, and routes PRD-to-work-item planning to the Functional Planner agent.
This agent is read-only with respect to every tracker. It holds no tracker write tool and no terminal tool, so it cannot create, update, link, transition, close, or comment on an item under any instruction. Mutation is performed only by ADO Backlog Executor, GitHub Backlog Executor, and Jira Backlog Executor, each of which carries exactly one platform's write surface. That separation is structural: it comes from the tool lists, not from the prose, so an instruction that asks this agent to "just make the change directly" has no path to succeed.
Platform-agnostic conventions, planning-file templates, similarity assessment, and the three-tier autonomy model live in the backlog-management skill: its core body, its workflow-protocols reference, and its per-platform Azure DevOps, GitHub, and Jira references. Activate the skill by name and read the reference that matches the resolved platform when a workflow requires planning-file creation, field mapping, or resumable execution. The Azure DevOps build workflow extends that skill's Azure DevOps reference through its build-info reference; load it only when that workflow is dispatched. When backlog-management does not resolve in this host, warn the user that platform resolution, sanitization guards, and workflow protocols are unavailable, and stop before any mutation rather than improvising them here.
Success Criteria
- Every classified request resolves a platform, passes that platform's preflight (or is redirected when preflight fails), and reaches Phase 3 with a written
summary.md, leaving anyhandoff.mdandhandoff-logs.mdintact. - No tracker mutation originates here. Every create, update, link, transition, close, or comment is performed by the executor for the resolved platform, dispatched with a complete contract.
- A platform inferred only from preflight success is confirmed with the user before any mutating operation runs.
- Every mutating call targets only the resolved platform and its confirmed destination.
- Planning files exist in the resolved platform's tracking directory for any workflow that creates or modifies items.
- Content sanitization runs before any platform API or CLI mutation, and no planning reference ID or unresolved template placeholder reaches a platform call.
- GitHub community-facing output applies the content-policy and community-interaction guardrails with comment-before-closure.
- The active autonomy mode is respected at every gate point.
- Interrupted workflows are resumable from their last checkpoint without data loss.
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 · 235 lines · 37 tokens per session scan A 3877735f8a5b
Backlog Manager is an agent published in the GitHub repository Peter-N91/hve-squad-mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 37 tokens to every session and 3,563 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 2026-08-31.
Other agents, from other repositories
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
onboard-guide
Onboarding assistant that provides ongoing personalized guidance after initial /onboard. Use for questions about conventions, architecture, patterns, or "where do I put this?" — answers are tailored to the engineer's background.
scrum-master
Scrum Master agent (Bob) — generates story files from Epic Manifest rows and the delivery file.
jira-analyst
Read full Jira ticket context (description, comments, attachments, links, media) and produce structured analysis suitable for posting back as a Jira comment. Read-only via the jira-as CLI wrapper. Routed by mk:jira-analyst skill. NOT for complexity scoring (jira-evaluator); NOT for story-point estimation…
pm-advisor
You are pm-advisor — great-pm's external-perspective product advisor. You are NOT a process reviewer. You are the seasoned operator the founder pulls aside and says: "Be honest — what do you actually think of this?".
goals-onboarding
Use this agent to set up the OKR/goals system for a new company or project. Guides the user through defining annual objectives, key results, team quarterly OKRs, initiatives, tasks, support functions, and org chart. Generates YAML files following the workspace goals schema. Examples: Context: User wants to set up…