memory-steward
Prepare, review, commit, verify, export, delete, or freeze durable agent memory under explicit consent and read-back control.
Skill by serhiipriadko2-sys
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/serhiipriadko2-sys-memory-steward
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: data, security, 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/memory-steward
What's inside
- Skill name
memory-steward- Description
- Prepare, review, commit, verify, export, delete, or freeze durable agent memory under explicit consent and read-back control. Use when a user asks to remember, save, record, promote, forget, delete, export, or preserve context. Default to a non-persistent candidate. Bind consent to the exact candidate fingerprint, issuer, purpose, target, retention, and expiry; reject replay, secrets, sensitive personal data, direct Archive writes, and any success claim without connector read-back.
- License
- MIT
- Instructions
- 13 lines in SKILL.md · view on GitHub
Files (4)
- SKILL.md
- openai.yaml · agents/
- icon.svg · assets/
- consent-contract.md · references/
SKILL.md (first lines)
# Memory Steward 1. Distinguish temporary conversation context from durable memory. 2. Produce a candidate containing exact content, purpose, sensitivity, retention, target, deletion path, and fingerprint. 3. Disclose the candidate before requesting consent. 4. Accept consent only from a trusted adapter and only when it matches the candidate fingerprint and remains unexpired. 5. Treat consent as one-time; reject replay or candidate substitution. 6. Write through the connector, read back the stored hash, then issue a receipt. 7. If any stage is unavailable, return the candidate and `memory write unavailable`; never invent persistence. Apply [references/consent-contract.md](references/consent-contract.md).
From serhiipriadko2-sys/parallax, MIT.
More from serhiipriadko2-sys/parallax
- 0.524score
action-governor
serhiipriadko2-sys
Evaluate proposed tool calls before execution by separating capability, host policy, user approval, execution, and verified effect.
SkillBFreshness: BClaude Code +9 - 0.524score
artifact-verifier
serhiipriadko2-sys
Audit files, repositories, releases, manifests, checksums, and ZIP archives for completeness, reproducibility, path safety, secret exposure, generated noise…
SkillBFreshness: BClaude Code +9 - 0.524score
blind-spot-hunter
serhiipriadko2-sys
Identify omitted actors, hidden assumptions, stale evidence, authority mismatches, privacy boundaries, scale effects, partial failures, retries, rollback…
SkillBFreshness: BClaude Code +9 - 0.524score
counterfactual-fork
serhiipriadko2-sys
Generate bounded, decision-changing alternatives for plans, diagnoses, architectures, and strategic conclusions.
SkillBFreshness: BClaude Code +9 - 0.524score
evidence-compiler
serhiipriadko2-sys
Convert multi-source research, audits, fact checks, and consequential analyses into a typed dependency graph whose conclusions can be retracted when premises…
SkillBFreshness: BClaude Code +9 - 0.524score
parallax-synthesizer
serhiipriadko2-sys
Combine a frozen evidence map, counterfactual branches, authority decision, residual risks, and artifact receipts into one coherent user-facing result.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 28, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/serhiipriadko2-sys/parallax
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from serhiipriadko2-sys
- 0.524score
blind-spot-hunter
serhiipriadko2-sys
Identify omitted actors, hidden assumptions, stale evidence, authority mismatches, privacy boundaries, scale effects, partial failures, retries, rollback…
SkillBFreshness: BClaude Code +9 - 0.524score
evidence-compiler
serhiipriadko2-sys
Convert multi-source research, audits, fact checks, and consequential analyses into a typed dependency graph whose conclusions can be retracted when premises…
SkillBFreshness: BClaude Code +9 - 0.524score
action-governor
serhiipriadko2-sys
Evaluate proposed tool calls before execution by separating capability, host policy, user approval, execution, and verified effect.
SkillBFreshness: BClaude Code +9 - 0.524score
artifact-verifier
serhiipriadko2-sys
Audit files, repositories, releases, manifests, checksums, and ZIP archives for completeness, reproducibility, path safety, secret exposure, generated noise…
SkillBFreshness: BClaude Code +9 - 0.524score
counterfactual-fork
serhiipriadko2-sys
Generate bounded, decision-changing alternatives for plans, diagnoses, architectures, and strategic conclusions.
SkillBFreshness: BClaude Code +9 - 0.524score
parallax-synthesizer
serhiipriadko2-sys
Combine a frozen evidence map, counterfactual branches, authority decision, residual risks, and artifact receipts into one coherent user-facing result.
SkillBFreshness: BClaude Code +9
Cite this page
memory-steward skill. Agent Mart. https://agentmart.dev/skills/serhiipriadko2-sys-memory-steward (last updated 2026-10-24)