Install
$ agentstack add skill-archcore-ai-plugin-plan ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
/archcore:plan
Plan a feature or initiative through one gated track. Vision types are the primary output. Reads cover all three categories: vision supplies intent and resumption targets, knowledge supplies constraints, experience supplies precedent.
When to use
- "Plan the auth redesign" →
sddtrack - "Create a roadmap for the API migration" →
sddtrack - "Plan a new feature for CSV export" →
sddtrack - "Just a plan, skip the idea and PRD" →
sddtrack; gates an existing document covers close viaskip_when, the rest run question-free - "I need market research before we plan" →
requirements-cascadetrack, sources mode - "We're regulated — start the ISO requirements cascade" →
requirements-cascadetrack, iso mode - "Investigate X before we plan" / "Compare the alternatives for Y" →
researchtrack
Not plan:
- Recording a decision →
/archcore:document - Documenting existing code →
/archcore:document - Codifying a team standard →
/archcore:document - Checking documents against code →
/archcore:review
Routing table
| Signal | Route | |---|---| | Default — feature, initiative, refactor, roadmap | sdd track — skills/_shared/tracks/sdd.md, entry sdd.frame | | Market research, discovery, competitive or opportunity analysis, stakeholder alignment — when it opens a requirements cascade (mrd → brd → urd); standalone market research as evidence routes to the research row below | requirements-cascade track, sources mode — skills/_shared/tracks/requirements-cascade.md, entry requirements-cascade.mrd | | Regulated system, ISO 29148, audits, formal or traceable requirements | requirements-cascade track, iso mode — skills/_shared/tracks/requirements-cascade.md, entry requirements-cascade.brs | | Technical research: investigate an unknown, compare alternatives, gather evidence before planning or deciding — "investigate X", "research the options for Y". Market and business discovery stays on the sources row above; a request that already proposes a specific target for team acceptance ("should we switch to Y", "let's adopt Y") belongs to /archcore:document's decision track — research is pre-decision evidence gathering with no proposed verdict | research track — skills/_shared/tracks/research.md, entry research.frame | | The user names a track or mode (sdd, sources, iso, research) in the invocation | The named path, with no routing | | "Just a plan" or "only the plan document" | sdd track — gates whose topic an existing document already covers close through skip_when; otherwise upstream gates run question-free when the request text satisfies their entry conditions | | A decision surfaces at a gate | Record the adr through the decision track (skills/_shared/tracks/decision.md), then return to the open gate |
Finer mode selection inside requirements-cascade — document-graph state, a named cascade document type — belongs to that track's Mode selection section.
Execution
1. Ground
Complete this step before asking the user any question.
- Search
.archcore/withmcp__archcore__search_documentsandmcp__archcore__list_documentsacross all three categories. Pass a planning-moment type filter — for exampletypes=["idea", "prd", "plan", "spec", "rnd", "rfc", "adr", "rule", "task-type", "cpat"]— instead of relying on the global type ranking. Do not exclude a category from reads. - WHEN a found document carries
implementsorrelatedrelations, pull the linked documents one hop viamcp__archcore__list_relationsandmcp__archcore__get_document. - WHEN a found draft on the topic carries an
archcore:trackstate block, resume it per the resume rules inskills/_shared/gate-contract.mdinstead of opening a new track. - Read git state — current branch, recent commits, working tree — and the code areas the topic names. Record the concrete files and modules for Step 5.
- IF
.archcore/exists but contains no documents, THEN proceed on outer-context grounding (git state and the codebase) and report that zero documents were found. - IF
.archcore/does not exist, THEN announce initialization in one line and callmcp__archcore__init_projectwithout asking a question.
Global sources. If a list_documents / search_documents result has global: true / read_only: true / source_kind: "global", load skills/_shared/globals.md. Never modify a global document and never target one with add_relation. Absent any global match, proceed as usual.
2. Route
Apply the routing table to the request text and the grounding results. WHEN the user names a track or mode in the invocation, execute that path with no routing — this is the expert invocation.
3. Budget
Interview mechanics, question form, and ceilings: skills/_shared/elicitation-contract.md. Auto mode draws every question from the shared per-invocation ceiling; an expert invocation raises per-gate budgets to the maxima the track file declares.
4. Execute the track
Run the routed track's gates per skills/_shared/gate-contract.md: evaluate skip_when first at every gate, keep track state only in the archcore:track block inside the draft artifact, persist each gate close in one mcp__archcore__update_document call, and follow the resume rules on re-entry. Gate bodies, per-gate questions, and relation wiring live in the track files — do not restate them.
5. Map tasks to files
WHEN the track has exited and a plan document exists:
- Annotate each task in the plan's Tasks section with the concrete files or modules that grounding surfaced for it, using
@path/to/filenotation, in onemcp__archcore__update_documentcall. - WHEN grounding surfaced no file or module for a task, state that no target was found for that task. Do not guess a path.
WHEN the track produced no plan document (sources and iso modes, and the research track), skip to Result — the track's exit gate names its follow-ups.
6. Implement fork
Offer exactly two exits and let the user choose:
- Implement now — start on the mapped task list, first phase first, against the files mapped in Step 5.
- Stop here — the draft documents and relations stay in
.archcore/; a later/archcore:planinvocation resumes any draft that still carries a state block.
Result
Report:
- Produced documents grouped by category — vision, knowledge, experience — with each document's path and status.
- Relations created, plus candidate
mcp__archcore__add_relationtargets among existing documents, or a statement that none match. - Next actions, naming only v2 commands:
/archcore:planto continue a cascade (for example aprdthrough thesddtrack after sources mode),/archcore:documentto record a decision or document code touched during implementation,/archcore:reviewto check the implementation against the recorded plan.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: archcore-ai
- Source: archcore-ai/plugin
- License: Apache-2.0
- Homepage: https://archcore.ai/plugin/
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.