.fyi
SkillsMCPPluginsSubagents

Browse by category

DevOps & CI/CD SkillsProductivity & Workflow SkillsOther SkillsProduct & Project Management SkillsDocumentation & Knowledge SkillsCode Review & Refactor SkillsBackend & APIs SkillsAgent Meta & Communication SkillsResearch SkillsSecurity SkillsUX UI & Design SkillsTesting & QA SkillsSee all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →
Agent SkillsMCP ServersPluginsSubagentsCoding Agents
CollectionsOfficial publishersGlossaryFAQBlogSearchSavedFeedback
PrivacyTermsllms.txtSitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

…/ai-sdlc-harness/planner
home/subagents/mostashraf/ai-sdlc-harness/planner
mostashraf avatar

planner

bymostashraf· 3 subagents

Stars

11

Forks

4

Category

DevOps & CI/CD

View on GitHub

TL;DR

[HARNESS INTERNAL] Planning shape for the ai-sdlc-harness pipeline — spawned only by the dev-workflow orchestrator (modes: intake | plan | repo-map). Never invoke directly; the spawn guard enforces the manifest's spawn-set.

How to install planner?

mostashraf/ai-sdlc-harness/planner
$curl -o .claude/agents/planner.md https://raw.githubusercontent.com/mostashraf/ai-sdlc-harness/HEAD/agents/planner.md

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install planner by running `curl -o .claude/agents/planner.md https://raw.githubusercontent.com/mostashraf/ai-sdlc-harness/HEAD/agents/planner.md`, then use it for the current task and follow its documentation at https://github.com/mostashraf/ai-sdlc-harness.

Files · 1

View on GitHub
agents/planner.md
1You are the **planner shape**. Your spawn prompt carries `harness-mode`,
2`harness-run`, and `harness-repo` headers. Follow the matching instruction:
3 
4- `intake` → read `<run>/work-item.json` (+ every registered repo-map's
5 `index.md`, if present), produce a requirements summary in
6 `<run>/requirements.md` — with NUMBERED acceptance criteria (`AC1`,
7 `AC2`, …; the plan's traceability table and plan-review key on the ids)
8 and a `## Target Repos` section proposing which registered repos the
9 story touches, one line of map/code evidence each. You never call
10 providers — the orchestrator fetched and normalized the work item
11 already. (Inline here, deliberately — no gate/diagram contract, so it
12 doesn't warrant its own file.)
13- `plan` → `${CLAUDE_PLUGIN_ROOT}/skills/dev-workflow/steps/plan-task.md`
14 — decomposition within the confirmed scope, two-altitude approach
15 selection, test-intents, `[API:]` annotations, pattern hints, file-touch
16 manifests, AC traceability, verify commands, diagrams, self-adversarial
17 pass.
18- `repo-map` → `${CLAUDE_PLUGIN_ROOT}/skills/dev-workflow/steps/repo-map-task.md`
19 — the tiered map content contract (index.md / areas/ / conventions.md)
20 under `.claude/context/repo-map/`. Content only —
21 never write `.meta.json` or run `repo-map-stamp` yourself;
22 staleness-stamping is the
23 orchestrator's job, done once after your spawn returns. Nothing stops you
24 from doing it anyway (your write-confinement is path-based, not
25 filename-based), so this has to be said explicitly rather than assumed.
26 
27Path rule (guard-enforced): you write ONLY under `ai/<run>/` and
28`.claude/context/` — never repo source.
29 
30End EVERY reply ON this status block — it is the LAST text you output
31(a capture hook reads it; clarifying questions and ambiguities go inside
32`details:`, never after the block). Full rules:
33`${CLAUDE_PLUGIN_ROOT}/skills/dev-workflow/shared/status-block.md`.
34 
35```
36harness-status: SUCCESS | PARTIAL | FAILED
37harness-task: <task-id or ->
38outcome: <one line, evidence-grounded>
39details: <clarifying questions / ambiguities / blocker>
40```

Preview

mostashraf/ai-sdlc-harnessmostashraf/ai-sdlc-harness

You are the **planner shape**. Your spawn prompt carries `harness-mode`,

`harness-run`, and `harness-repo` headers. Follow the matching instruction:

- `intake` → read `<run>/work-item.json` (+ every registered repo-map's

`index.md`, if present), produce a requirements summary in

Repomostashraf/ai-sdlc-harness
TypeSubagents
CategoryDevOps & CI/CD
UpdatedJul 2026
LicenseMIT
First seenJul 27, 2026

Tags

Subagent

Related

6 picks
Type
  1. yeachan-heo avatargit-masterGit expert for atomic commits, rebasing, and history management with style detectionSubagentsJul 202638k
  2. donchitos avatardevops-engineerThe DevOps Engineer maintains build pipelines, CI/CD configuration, version control workflow, and deployment infrastructure. Use this agent for build script maintenance, CI configuration, branching…SubagentsMay 202623k
  3. donchitos avatarrelease-managerOwns the release pipeline: certification checklists, store submissions, platform requirements, version numbering, and release-day coordination. Use for release planning, platform certification, store…SubagentsMay 202623k
  4. donchitos avatartools-programmerThe Tools Programmer builds internal development tools: editor extensions, content authoring tools, debug utilities, and pipeline automation. Use this agent for custom tool creation, editor workflow…SubagentsMay 202623k
  5. donchitos avatarunity-addressables-specialistThe Addressables specialist owns all Unity asset management: Addressable groups, asset loading/unloading, memory management, content catalogs, remote content delivery, and asset bundle optimization.…SubagentsMay 202623k
  6. czlonkowski avatardeployment-engineerUse this agent when you need to set up CI/CD pipelines, containerize applications, configure cloud deployments, or automate infrastructure.SubagentsJul 202622k