spec-agent-memory
Read and update project agent memory in .agents/memory/.
Skill by sushilti80
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/sushilti80-spec-agent-memory
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/spec-agent-memory
What's inside
- Skill name
spec-agent-memory- Description
- Read and update project agent memory in .agents/memory/. Use at start and end of subagent work for PRD, ARCH, codebase, and recipe learnings.
- License
- MIT
- Instructions
- 62 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Spec agent memory Project-scoped memory lives in **`.agents/memory/`** (commit to git for team continuity). Cursor resolves the same content via `.cursor/agent-memory/` symlink. ## At session start 1. Read `.agents/memory/_project/MEMORY.md` (shared context). Cursor may inject a short summary — still open the file if you need full detail. 2. Read `.agents/memory/_project/specs-index.md` (REQ/ARCH/BUG status). 3. Read `.agents/memory/<agent-name>/MEMORY.md` for your role (e.g. `backend-engineer`). Create the file if missing (`# <role> memory` + `## Lessons`). ## What to record - PRD/REQ features and implementation status - Architecture decisions and component relationships (link ARCH/ADR paths) - Codebase patterns, module locations, conventions - Test patterns and common failure modes - Phase/feature dependencies - Useful technology notes from research (with links) - Config and environment variable dependencies - Blockers and known issues - **Recipe** used (`bug-fix`, `maintenance`, etc.) and outcome ## File layout | Path | Purpose | |------|---------| | `_project/MEMORY.md` | Shared — stack, conventions, links (keep ≤200 lines) | | `_project/specs-index.md` | Table of REQ/ARCH/BUG status | | `<agent-name>/MEMORY.md` | Role-specific durable notes | | `<agent-name>/<topic>.md` | Deep dives; link from MEMORY.md | ## Guidelines - Keep **`MEMORY.md` concise** — aim under **200 lines** (long files dilute attention). - Use **topic files** (`debugging.md`, `patterns.md`, `infra.md`) for detail; link from MEMORY.md. - Update or **delete** outdated memories. - Organize by **topic**, not chronology. - **Never store secrets**, tokens, or credentials. - Prefer **paths and facts** over narrative; specs in `.specs/` remain source of truth — memory is an index, not a replacement. ## Learning journal (Cursor plugin hooks) Cursor plugin hooks append to `_project/learning-journal.md` on spec/memory edits. **Distill** durable entries into `MEMORY.md`; delete noise from the journal periodically. Other tools: append manually or follow `SPECFORGE_HOME/MULTI-TOOL.md` checkpoint checklist. ## At session end 1. Update your agent `MEMORY.md` with new learnings. 2. Update `_project/specs-index.md` if spec status changed. 3. If a lesson applies to all agents, add one line to `_project/MEMORY.md`. 4. At **gate boundaries**, orchestrator writes checkpoint to `.specs/handoffs/`; do not rely on chat for next phase (Principle 8). ## HANDOFF addition Add to HANDOFF when relevant: ```markdown **Memory updated:** - `.agents/memory/<agent>/MEMORY.md` - [other files] ```
From sushilti80/specforge-engineering-team, MIT.
More from sushilti80/specforge-engineering-team
- 0.524score
ui-a11y
sushilti80
Accessibility checklist for interactive UI: labels, keyboard, focus, contrast, and ARIA for overlays.
SkillBFreshness: BClaude Code +9 - 0.524score
spec-advisory
sushilti80
Readonly advisory mode — architecture review, compare options, feasibility, "should we", "critical review", "worth it", "review only".
SkillBFreshness: BClaude Code +9 - 0.524score
ui-forms
sushilti80
Build working forms: schema validation, field errors, submit/pending/disabled states, and accessible labels.
SkillBFreshness: BClaude Code +9 - 0.521score
spec-agent-audit
sushilti80
Readonly audit of agent definition files in agents/ for memory & self-learning patterns, debugging patterns, description alignment, and contradicting…
SkillBFreshness: BClaude Code +9 - 0.521score
spec-challenger
sushilti80
Adversarial review of REQ or ARCH (or consequential ADR) with capped rounds.
SkillBFreshness: BClaude Code +9 - 0.521score
spec-guardian-drift
sushilti80
Readonly compare .specs/ to codebase and flag drift.
SkillBFreshness: BClaude Code +9 - 0.521score
spec-handoff
sushilti80
Standard HANDOFF block and checkpoint files for spec-driven pipeline.
SkillBFreshness: BClaude Code +9 - 0.521score
spec-arch-author
sushilti80
Write ARCH specs and ADRs from user-APPROVED REQ files.
SkillBFreshness: BClaude Code +9 - 0.521score
spec-recipes
sushilti80
Need-based workflow recipes for eng-orchestrator.
SkillBFreshness: BClaude Code +9 - 0.521score
spec-release-metrics
sushilti80
Record release efficiency against need-based plans: planned vs run agents, estimated tokens (minimal mode), human gates, quality KPIs.
SkillBFreshness: BClaude Code +9 - 0.521score
spec-req-author
sushilti80
Write or update REQ specs in .specs/requirements/.
SkillBFreshness: BClaude Code +9 - 0.521score
spec-token-budget
sushilti80
Token and output budgets by task type.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 4, 2026 (3 months ago)
- Last release
- Aug 6, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from sushilti80
- 0.524score
ui-a11y
sushilti80
Accessibility checklist for interactive UI: labels, keyboard, focus, contrast, and ARIA for overlays.
SkillBFreshness: BClaude Code +9 - 0.524score
ui-forms
sushilti80
Build working forms: schema validation, field errors, submit/pending/disabled states, and accessible labels.
SkillBFreshness: BClaude Code +9 - 0.524score
spec-advisory
sushilti80
Readonly advisory mode — architecture review, compare options, feasibility, "should we", "critical review", "worth it", "review only".
SkillBFreshness: BClaude Code +9 - 0.521score
spec-guardian-drift
sushilti80
Readonly compare .specs/ to codebase and flag drift.
SkillBFreshness: BClaude Code +9 - 0.521score
spec-challenger
sushilti80
Adversarial review of REQ or ARCH (or consequential ADR) with capped rounds.
SkillBFreshness: BClaude Code +9 - 0.521score
spec-arch-author
sushilti80
Write ARCH specs and ADRs from user-APPROVED REQ files.
SkillBFreshness: BClaude Code +9
Cite this page
spec-agent-memory skill. Agent Mart. https://agentmart.dev/skills/sushilti80-spec-agent-memory (last updated 2026-10-24)