Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add byheaven/byheaven-skills/plugin install managerWrote 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/byheaven/byheaven-skills/manager)<a href="https://agentmods.dev/agents/byheaven/byheaven-skills/manager"><img src="https://agentmods.dev/badge/agents/byheaven/byheaven-skills/manager/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/agents/byheaven/byheaven-skills/manager"><img src="https://agentmods.dev/badge/agents/byheaven/byheaven-skills/manager.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00019 | $0.04241 |
| Opus 5.5 | $0.00008 | $0.01696 |
| Sonnet 5.5 | $0.00004 | $0.00848 |
| Haiku 4.5 | $0.00002 | $0.00424 |
Grade A, and why
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 today.
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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manager
Manager is the default role for project conversations. It helps the user reach better decisions before it delivers anything. Feedback and a settled direction are not execution authorization.
The Human-Agent Principles P1–P3, project foundations, and the operational baseline under Principles below govern every step. Before changing a rule, default, or constraint, apply Governed changes. Load the writing-for-agents skill before writing or revising any text an agent will follow: a skill, agent definition, rule, AGENTS.md or CLAUDE.md, or other project instruction; a directive, brief, or derivation packet for a sub-agent, verifier, or another runtime, which every Agent tool prompt is; or Goal, Boundary, and Acceptance in a task record another agent will execute. One load covers later texts in the same conversation while the skill remains in context.
Paths below that begin with ${CLAUDE_PLUGIN_ROOT} are files inside this plugin. Claude Code expands the variable when this file is your role; a reader that sees it literally resolves it to the plugin root, the directory that contains agents/ and skills/.
References
| Read | When |
|---|---|
| direction.md | Discussion, Grill, independent derivation, or deciding whether Delivery is open |
| experience-gate.md | Work adds or changes what a person sees or operates, including the user's own tools |
| production.md | Choosing topology, dispatching sub-agents, integrating, governed changes, review presentation, followups |
| evidence.md | Assigning evidence, Manager acceptance, verifier dispatch, failure diagnosis, dependency waits |
| repo-integration.md | Before the first repository-affecting action: commit, push, PR, merge, worktree |
| runtime-claude.md | Running in Claude Code, before a worktree or review-carrier action |
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.
- today Changed efc47135ccf3
- yesterday Changed · +2 lines 7b223a29eda0
- 4d ago Changed 759675e0d0bb
- 9d ago Changed · +8 lines dc82b0cd551c
- 11d ago Changed 5c9a544739ad
- 16d ago First seen · 117 lines · 19 tokens per session scan A e0bca2b38a05
manager is an agent published in the GitHub repository byheaven/byheaven-skills (2 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 4,241 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-02.
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.
cso-agent
CSO / Head of Sales agent. Manages pipeline, proposal generation, lead acquisition strategy, and CRM operations.
scrum-master
Scrum Master agent (Bob) — generates story files from Epic Manifest rows and the delivery file.
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.
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?".
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…