opencontext
Manage AI Project Memory with OpenContext
AI agents lose project context between sessions, causing repeated explanations and stale assumptions. This skill guides Claude, Codex, and Claude Code to store, search, and reuse OpenContext knowledge.
Stop for confirmation before installing.
Review the plan and obtain explicit user consent before changing files.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "opencontext" from https://skillstore.io/skills/supercent-io-opencontext.md and its manifest at https://skillstore.io/api/skills/supercent-io-opencontext/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "opencontext". Load context before implementing a payment API change.
Expected outcome:
The agent summarizes stored API contracts, prior payment decisions, known pitfalls, and documents that should be read first.
Using "opencontext". Search for previous lessons about flaky integration tests.
Expected outcome:
The agent returns matching notes, relevant folders, document titles, and a short explanation of each result.
Using "opencontext". Store conclusions after a refactor.
Expected outcome:
The agent records the final design choice, validation steps, unresolved risks, and next actions in project memory.
Security Audit
High RiskMost static findings are false positives from Markdown backticks, reference links, and documented local paths. The real risks are persistent storage of project context, user-level agent configuration changes, and third-party CLI execution. No evidence found of prompt injection, credential exfiltration, or covert network calls.
Confirmed security concerns (3)
Risk Factors
⚙️ External commands (50)
🌐 Network access (7)
📁 Filesystem access (22)
🔑 Env variables (1)
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/supercent-io-opencontext/audits/6?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/supercent-io-opencontext?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/supercent-io-opencontext?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/supercent-io-opencontext/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/supercent-io-opencontext.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
supercent-io. (2026). opencontext security audit report (audit version 6) [Author version 1.0.0]. Skillstore. https://skillstore.io/skills/supercent-io-opencontext/audits/6BibTeX citation
@techreport{supercent-io-supercent-io-opencontext-2026,
author = {supercent-io},
title = {opencontext security audit report (audit version 6)},
institution = {Skillstore},
year = {2026},
number = {6},
url = {https://skillstore.io/skills/supercent-io-opencontext/audits/6},
note = {Author version 1.0.0}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "opencontext security audit report (audit version 6)"
version: "1.0.0"
type: report
authors:
- name: "supercent-io"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/supercent-io-opencontext/audits/6"
identifiers:
- type: other
value: "skillstore:supercent-io-opencontext:audit:6"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: MediumWhat You Can Build
Resume Project Work
Load prior architecture notes, decisions, and pitfalls before changing code.
Share Agent Research
Store analysis findings so other agents can reuse the same project knowledge.
Maintain Project Memory
Record acceptance criteria, API contracts, and dependency decisions after each work session.
Try These Prompts
Use OpenContext to load the most relevant background for this repository. Summarize decisions, pitfalls, and next steps before coding.
Search OpenContext for previous decisions about this feature. Return the most relevant notes, citations, and unresolved questions.
Create or update an OpenContext document with session decisions, files changed, tests run, risks, and recommended follow-up work.
Use OpenContext as the shared memory layer. Load existing context, assign research topics, merge findings, and store final conclusions with citations.
Best Practices
- Load OpenContext before starting work that depends on prior decisions.
- Store concise conclusions with citations, dates, and clear next steps.
- Review context before reuse and remove outdated or sensitive information.
Avoid
- Do not store credentials, tokens, private keys, or regulated personal data.
- Do not run initialization commands without reviewing the files they may modify.
- Do not rely on stale context when source files or requirements have changed.
Frequently Asked Questions
What does this skill help an AI agent remember?
Does it work with Claude, Codex, and Claude Code?
Do I need the OpenContext CLI?
Can it search stored documents?
Where is context stored?
What should I avoid storing?
Developer Details
Author
supercent-ioLicense
MIT
Author version
v1.0.0
Skillstore revision
r1
Ref
0519034dad657fb1f7706e0550e962beeda73fdf
Maintenance freshness
7/18/2026
Usage
14 downloads · 148 views
File structure
📄 SKILL.md