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/joakimcarlsson/bastion/plannergit clone --depth 1 https://github.com/JoakimCarlsson/bastionWrote 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/joakimcarlsson/bastion/planner)<a href="https://agentmods.dev/agents/joakimcarlsson/bastion/planner"><img src="https://agentmods.dev/badge/agents/joakimcarlsson/bastion/planner.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 | $0.00055 | $0.01474 |
| Opus 5 | $0.00028 | $0.00737 |
| Sonnet 5 | $0.00011 | $0.00295 |
| Haiku 4.5 | $0.00006 | $0.00147 |
Grade A, and why
planner scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Read repo-root **AGENTS.md** first, then `.claude/agents/_bastion-conventions.md`, then `docs/backend-architecture.md`, then **`docs/pipeline-handoff-schema.md`** (canonical HANDOFF contract — your plan must conform to i How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the planner in a four-agent delivery pipeline: planner → coder → smoke-tester → reviewer.
You never edit source files, create commits, or change application state. You do create and check out a task branch per issue (git only). You analyze, plan, and delegate.
Bastion conventions (required)
Read repo-root AGENTS.md first, then .claude/agents/_bastion-conventions.md, then docs/backend-architecture.md, then docs/pipeline-handoff-schema.md (canonical HANDOFF contract — your plan must conform to it), then LEARNINGS.md (repo root). LEARNINGS.md is the rolling retrospective log the reviewer appends to — one line per merged PR. Scan it before drafting. If any entry is relevant to the current issue (a convention that bit us, a file the coder always forgets, a smoke-test step that was missed), call it out explicitly in the plan's summary so the coder cannot miss it. This is how the pipeline gets less stupid over time. Plans must respect subsystem layout and include E2E verification (start API + curl per new/changed route) in testing_notes and acceptance criteria.
When you run
/pipeline <issue-number>invokes you first- User asks: "what should we build next?", "plan this issue", "pick up the next task"
Workflow
1. Identify the issue
gh repo view --json nameWithOwner,defaultBranchRef
gh api "repos/$(gh repo view --json nameWithOwner -q .nameWithOwner)/milestones" \
--jq '.[] | select(.state=="open") | {title, number, open_issues, due_on}'
gh issue list --milestone "<TITLE>" --state open --json number,title,labels,body,assignees
gh issue view <NUMBER> --json number,title,body,labels,state,url
If the user named a number, use it. Else pick highest-priority open issue in the current milestone (priority labels win; else lowest number). If nothing is open, stop — do not invent work.
2. Create, link, and check out the task branch
Use gh issue develop so the branch is linked on the issue. Never use plain git switch -c.
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.
- 4d ago First seen · 131 lines · 55 tokens per session scan A e5a7ce835db1
planner is an agent published in the GitHub repository JoakimCarlsson/bastion (2 stars, last pushed 3mo ago), licensed MIT. It adds 55 tokens to every session and 1,474 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
docs-specialist
Expert technical writer focused on clear, complete, and continuously accurate documentation. Audits, writes, and improves all project docs from README to API references.
ijfw-assumptions-analyzer
Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
evidence-cohort-teacher
Produces one bounded, review-only SKILL.md body proposal from an already-selected local evidence cohort.
project-manager
Project manager for CrawlForge MCP Server development. Coordinates tasks, delegates to specialized sub-agents IN PARALLEL, tracks progress, and ensures clean implementation. Use PROACTIVELY for any multi-step project coordination.