Borrowing it
Nothing to install: this file belongs to cp-yu/cc-switch-web. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cp-yu/cc-switch-web/main/.github/prompts/opsx-archive.prompt.mdgit clone --depth 1 https://github.com/cp-yu/cc-switch-webWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/cp-yu/cc-switch-web/opsx-archive)<a href="https://agentmods.dev/commands/cp-yu/cc-switch-web/opsx-archive"><img src="https://agentmods.dev/badge/commands/cp-yu/cc-switch-web/opsx-archive/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/cp-yu/cc-switch-web/opsx-archive"><img src="https://agentmods.dev/badge/commands/cp-yu/cc-switch-web/opsx-archive.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00008 | $0.02630 |
| Opus 5.5 | $0.00003 | $0.01052 |
| Sonnet 5.5 | $0.00002 | $0.00526 |
| Haiku 4.5 | $0.00001 | $0.00263 |
Grade A, and why
opsx-archive scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Archive a completed change in the experimental workflow.
Input: Optionally specify a change name after /opsx:archive (e.g., /opsx:archive add-auth). If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
When archive guidance discusses embedded sync or artifact write-back, treat openspec/config.yaml as the compact source of truth and follow the shared prompt/runtime projection contract rather than reinterpreting raw config keys inside the template body.
Steps
-
If no change name provided, prompt for selection
Run
openspec list --jsonto get available changes. Use the AskUserQuestion tool to let the user select.Show only active changes (not already archived). Include the schema used for each change if available.
IMPORTANT: Do NOT guess or auto-select a change. Always let the user choose.
-
Unified Full Verify Gate
Run the CLI gate:
openspec verify status "<change-name>" --json
Verify Result Freshness Rules:
A verify result is considered FRESH if ALL of the following hold:
.verify-result.jsonexists in the change directoryverificationContext.evidenceFingerprintmatches the current workspace fingerprintverificationContext.contractVersionis"1.0"resultisPASSorPASS_WITH_WARNINGS
A verify result is considered STALE if ANY of the following hold:
verificationContext.evidenceFilesis missing or the file list changedverificationContext.evidenceFingerprintdoes not match the recomputed fingerprintverificationContext.gitHeadCommitdoes not match the current HEAD (if recorded)verificationContext.contractVersionis missing or not"1.0"resultis notPASSorPASS_WITH_WARNINGS
Optimization metadata compatibility:
optimizationmetadata is advisory for archive gating, not part of the freshness hash inputs- Legacy verify results without
optimizationmay still be fresh if every freshness rule above passes - If
optimization.statusexists, evaluate its acceptability separately from freshness
When verify result is STALE or MISSING:
- Archive MUST execute full verify before continuing
- Do NOT attempt to repair or reuse a stale verify result
Fingerprint Computation:
- Sort
evidenceFilesalphabetically before hashing - For each evidence file, collect normalized relative POSIX path + content hash
- Hash the JSON-serialized entries with SHA-256
- Use
path.join(),path.resolve(), andpath.normalize()for all path handling - Persist
evidenceFilesas relative POSIX paths for cross-platform comparison
Verify State Machine:
Phase 1 PASS / PASS_WITH_WARNINGS
|
v
PENDING_VERIFICATION
|-- no affectedFileHashes --> Phase 2 optimization analysis
| |-- NO_OPTIMIZATION_NEEDED --> NOT_NEEDED
| |-- SKIPPED / optimization.enabled=false --> SKIPPED
|-- affectedFileHashes ------> PENDING_VERIFICATION (optimization proposed)
|-- verification PASS --> IMPROVED
|-- verification FAIL_NEEDS_REMEDIATION --> retry or DEGRADED
|-- retries exhausted --> DEGRADED
Archive gate accepts: SKIPPED | NOT_NEEDED | IMPROVED | DEGRADED
Archive gate rejects: PENDING_VERIFICATION | ABORTED_UNSAFE
Verify CLI JSON Schema Reference:
| CLI call | --input JSON |
|---|---|
openspec verify phase1 "<change-name>" --input '<json>' --json |
{"result":"PASS","issues":[],"evidenceFiles":["..."],"executionMode":"..."} |
openspec verify phase2 "<change-name>" --type=optimization --input '<json>' --json |
{"status":"NO_OPTIMIZATION_NEEDED","summary":"..."} (summary is required, must be non-empty) |
openspec verify phase2 "<change-name>" --type=optimization --files "<affected-files>" --input '<json>' --json |
{"status":"OPTIMIZATION_PROPOSED","summary":"..."} |
openspec verify phase2 "<change-name>" --type=optimization --input '<json>' --json |
{"status":"SKIPPED"} |
openspec verify phase2 "<change-name>" --type=verification --input '<json>' --json |
{"result":"PASS","issues":[]} |
openspec verify phase2 "<change-name>" --type=verification --input '<json>' --json |
{"result":"FAIL_NEEDS_REMEDIATION","issues":[...],"behaviorRetryCounter":N} |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 206 lines · 8 tokens per session scan A 82492e4d2e05
opsx-archive is a command published in the GitHub repository cp-yu/cc-switch-web (47 stars, last pushed 1mo ago), licensed MIT. It adds 8 tokens to every session and 2,630 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-12.
Other commands, from other repositories
sync-coordinator
Multi-package synchronization and version alignment with ruv-swarm coordination for seamless integration between claude-code-flow and ruv-swarm packages.
land
Resolve and squash merge one named, currently authorized pull request.
sync-coordinator
Multi-package synchronization and version alignment with ruv-swarm coordination for seamless integration between claude-code-flow and ruv-swarm packages.
lavra-ship
Fully automated ship sequence from code-ready to PR-open with beads closed and knowledge captured.
github-modes
This document describes all GitHub integration modes available in Claude-Flow with ruv-swarm coordination. Each mode is optimized for specific GitHub workflows and includes batch tool integration for maximum efficiency.
gsd:ship
Create PR, run review, and prepare for merge after verification passes.