Strands Agents is an open-source SDK for building and running AI agents in Python and TypeScript. Developers use it to create agents with model providers, tools, lifecycle controls, memory, sessions, streaming, tracing, and evaluations, and the catalogue includes add-ons for its agent-building workflow.
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/strands-agents/harness-sdk/docs-plannernpx skills add strands-agents/harness-sdk --skill docs-plannergit clone --depth 1 https://github.com/strands-agents/harness-sdkWrote 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/strands-agents/harness-sdk/docs-planner)<a href="https://agentmods.dev/skills/strands-agents/harness-sdk/docs-planner"><img src="https://agentmods.dev/badge/skills/strands-agents/harness-sdk/docs-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 | $0.00073 | $0.00797 |
| Opus 5 | $0.00036 | $0.00398 |
| Sonnet 5 | $0.00015 | $0.00159 |
| Haiku 4.5 | $0.00007 | $0.00080 |
Grade A, and why
docs-planner 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 5d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Planner
Identify gaps in the docs site and produce a prioritized backlog.
Inputs
- Scope: Area to assess — all docs, a specific section, or a feature area. Default: all.
- Signals (optional): GitHub issues, community questions, support threads.
- Competitive context (optional): What competitors document that we don't.
Process
Step 1: Inventory current docs
Read site/src/config/navigation.yml for the full navigation tree — this is the authoritative navigation source for the Astro site, loaded by site/astro.config.mjs via site/src/sidebar.ts. Glob site/src/content/docs/**/*.{md,mdx} for all content files. Classify each by content type (tutorial, how-to, reference, explanation, mixed) and coverage area (quickstart, tools, agents, multi-agent, deployment, etc.).
Step 2: Identify gaps
Compare the inventory against:
- SDK surface area: Are all major features documented? Features without docs pages are gaps.
- Diataxis completeness: For each feature area, does documentation exist across all four types? A feature with reference but no tutorial has a gap.
- Community signals: If GitHub CLI is available, pull open issues labeled "documentation" from strands-agents/harness-sdk. Map questions to existing docs (unclear/hard to find) or missing docs (content gap).
- Competitive comparison (if provided): What do LangChain, CrewAI, Anthropic, and OpenAI document about equivalent features that we don't?
Step 3: Prioritize
Score each gap on developer impact and effort:
- P0 (do now): High impact, any effort. Quickstart, getting-started, core concepts.
- P1 (do soon): Medium impact, low effort. Missing how-to guides for common tasks.
- P2 (plan for): Medium impact, high effort. New tutorials, architectural explanations.
- P3 (backlog): Low impact. Niche scenarios, edge case documentation.
Step 4: Produce the backlog
Output as markdown:
## Docs Backlog: [Scope]
**Generated:** [date]
**Pages inventoried:** [count]
**Gaps identified:** [count]
### P0: Do Now
- [ ] [Task] — [content type] — [target page] — [reason]
### P1: Do Soon
- [ ] [Task] — [content type] — [target page] — [reason]
### P2: Plan For
- [ ] [Task] — [content type] — [target page] — [reason]
### P3: Backlog
- [ ] [Task] — [content type] — [target page] — [reason]
### Coverage Matrix
| Feature Area | Tutorial | How-To | Reference | Explanation |
|---|---|---|---|---|
| Agent basics | Y | ~ | Y | N |
| Custom tools | Y | Y | Y | N |
| Multi-agent | ~ | N | Y | ~ |
### Signal-Driven Insights
- [Theme from community signals mapped to specific doc gaps]
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.
- 5d ago First seen · 80 lines · 73 tokens per session scan A e1c3a19ec499
docs-planner is a skill published in the GitHub repository strands-agents/harness-sdk (7,141 stars, last pushed today), licensed Apache-2.0. It adds 73 tokens to every session and 797 once invoked, about $0.0004 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
github-triage
Triage GitHub issues through a label-based state machine with interactive grilling sessions. Use when user wants to triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.
backlog
Capture single backlog items, or list and triage an existing project backlog. Use this skill whenever the user wants to file a bug, feature request, or backlog item without writing a full PRD, including casual requests mid-conversation like "create an issue for that", "add this to the backlog", or "file a quick bug…
reframe-voice
Write, rewrite, or review content in the evidence-led reframe voice style. Use when the user explicitly asks to write in "reframe voice" or "reframe style". Do NOT use for general writing tasks.
to-tickets
Break a plan, spec, or the current conversation into independently-grabbable tickets on the project issue tracker using tracer-bullet vertical slices, each declaring the tickets that block it. Use when user wants to convert a plan or spec into tickets, create implementation tickets, or break down work into issues.
to-spec
Turn the current conversation context into a spec and submit it as a GitHub issue. Use when user wants to create a spec or PRD from the current context.
tasks
Decompose a PLAN / SPEC / FEAT / BUG / DEBT / CHORE into atomic TASK-NNN items ready for the implement flow, via a clean-context subagent. Use when PM mentions "create tasks", "generate TASKs", "break down into tasks", "tasks from PLAN", "break this into tasks", "декомпозиция", "сделай таски", or any request to…