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 agents/kunwarvivek/mcp-github-project-manager/issue-trackergit clone --depth 1 https://github.com/kunwarVivek/mcp-github-project-managerWhat 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 | $0.00836 |
| Opus 5 | $0.00000 | $0.00418 |
| Sonnet 5 | $0.00000 | $0.00167 |
| Haiku 4.5 | $0.00000 | $0.00084 |
Grade A, and why
issue-tracker 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 2d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Issue tracker: Beads (bd)
Issues for this repo live in beads, a local Dolt-backed issue database driven by the bd CLI.
This is a deliberate choice over GitHub Issues. CLAUDE.md mandates bd for all task
tracking, and the engineering skills follow that rule rather than fighting it.
The repo has a second, separate surface. GitHub Issues on
kunwarVivek/mcp-github-project-managerstill holds externally-reported bugs. That is a reporting surface for users; beads is the working tracker these skills operate on. Do not mirror between them automatically. If an external report needs work, open a bead for it and reference the GitHub issue number in the description.
Conventions
- Issue ids look like
mcp-github-project-manager-hb8.15— a project prefix, a parent id, then a child suffix. Always pass the full id. - Hierarchy is first-class:
bd create --parent=<id>makes a child. Use anepictype for the umbrella andtask/bug/featurefor children. - Priority is
0–4orP0–P4(0= critical,2= medium,4= backlog). Nothigh/medium/low— those are rejected. - Triage state is carried on labels (see
triage-labels.md), set with--labelsat create time or--add-labelon update. - Comments/history go in notes:
bd update <id> --append-notes "...". - Never run
bd edit— it opens$EDITORand blocks a non-interactive agent.
When a skill says "publish to the issue tracker"
bd create --title="..." --description="..." --type=task --priority=2 \
[--parent=<epic-id>] [--labels=needs-triage]
For a multi-ticket effort, create the epic first, then children with --parent, then wire
order with bd dep add <issue> <depends-on>.
When a skill says "fetch the relevant ticket"
bd show <id> # full detail incl. dependencies
bd list --status=open # everything open, as a tree
bd search "<query>" # keyword search
Wayfinding operations
Beads models this natively — no file conventions needed.
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.
- 2d ago First seen · 67 lines · 0 tokens per session scan A 485d0355b51b
issue-tracker is an agent published in the GitHub repository kunwarVivek/mcp-github-project-manager (95 stars, last pushed 22d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 836 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 2026-08-30.
Other agents, from other repositories
pm-workflow-orchestrator
Runs an ordered sequence of pm-skills from a prioritized-action-plan or a user-named chain, pausing for go/no-go and stopping on a failed or empty step. Explicit invocation only; never fires proactively.
pm-critic
Use proactively after any PM-artifact-producing skill completes (deliver-prd, foundation-meeting-recap, foundation-okr-writer, foundation-persona, foundation-lean-canvas, discover-interview-synthesis, define-problem-statement, define-hypothesis, deliver-edge-cases, deliver-user-stories, deliver-acceptance-criteria…
pm-release-conductor
Guided release runbook with 6 explicit gates (G0 Pre-tag readiness, G1 Adversarial review, G2 Version bump + CHANGELOG prep, G2.5 Commit release-prep + re-verify, G3 Tag + push, G4 Post-tag hygiene). Chains to pm-skill-auditor at G0 (and again at G2.5 verification) and to pm-changelog-curator at G2. Refuses to advance…
product-manager
Product management expert for roadmap decisions, feature prioritization, and scope management. Acts as a startup PM - ruthlessly prioritizes, focuses on speed over perfection. Use proactively for strategic product decisions.
council-facilitator
Turn verified disagreement into one product decision. Do not vote and do not average.
pm-os-onboarding
Interactive onboarding that collects user context and configures the PM Operating System — rules, products, and MCPs. Use when user says "onboard", "setup", "PM-OS setup", or "get started".