Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add pivoshenko/pivoshenko.ai --skill spec-archivegit clone --depth 1 https://github.com/pivoshenko/pivoshenko.aiWrote 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/skills/pivoshenko/pivoshenko.ai/spec-archive)<a href="https://agentmods.dev/skills/pivoshenko/pivoshenko.ai/spec-archive"><img src="https://agentmods.dev/badge/skills/pivoshenko/pivoshenko.ai/spec-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/skills/pivoshenko/pivoshenko.ai/spec-archive"><img src="https://agentmods.dev/badge/skills/pivoshenko/pivoshenko.ai/spec-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 | $0.00207 | $0.01982 |
| Opus 5.5 | $0.00083 | $0.00793 |
| Sonnet 5.5 | $0.00041 | $0.00396 |
| Haiku 4.5 | $0.00021 | $0.00198 |
Grade A, and why
spec-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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Archive
completed change -> gate -> archive -> specs updated -> commit -> PR.
The last link in spec-explore -> spec-propose -> spec-apply -> spec-verify -> spec-archive. /opsx:archive owns the OpenSpec mechanics and never branches, commits, or opens a PR. This skill owns that seam, plus the one gate the CLI declines to enforce. Never author spec content here.
Preconditions
openspec context --json
no_openspec_root -> stop, offer openspec init --tools claude, wait for the user. Never auto-init, never fall back to the current directory. Use the returned root.path as authoritative. User names a store -> openspec store list --json for ids, then --store <id> on every command that accepts one, sticky for the rest of the run.
Then two things must hold before anything is archived:
- The work is verified -
spec-verifyran and its gate passed. Not verified -> send the user there and stop. Why -> archiving folds the delta into the specs, so doing it before the code is proven makes the spec the fiction rather than the record - The tree is clean enough to commit the archive alone. Unrelated edits in flight -> commit or stash them first. Why -> the archive move and the spec fold are one commit, and a dirty tree drags someone else's work into it
The Gate
This is the point of this wrapper. Read the task progress before archiving, and never pass --yes without having read it:
openspec instructions apply --change "<name>" --json
state: "all_done", equivalently progress.remaining == 0 -> the gate passes. Anything else -> stop. Name every unticked task and send the user to spec-apply. Do not archive. Do not "just tick the boxes".
Do not gate on isComplete from openspec status --json. It reports that all four artifact FILES exist, not that any task is finished. Probed: a change with 1 of 3 tasks ticked reports isComplete: true while openspec instructions apply --json reports progress: {total: 3, complete: 1, remaining: 2}. Only the second one counts checkboxes.
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 · 131 lines · 207 tokens per session scan A 488a2befdaef
spec-archive is a skill published in the GitHub repository pivoshenko/pivoshenko.ai (6 stars, last pushed yesterday), licensed MIT. It adds 207 tokens to every session and 1,982 once invoked, about $0.0008 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 2026-09-16.
Other skills, from other repositories
comet-safe-delivery
A Chinese-language procedure for safely delivering specified Comet changes through Git. It covers checking worktrees and unrelated edits, staging exact files, validating hooks, and authorized commits or pushes.
loom-git-workflow
Git operations guidance including branching strategies, commit conventions, merge workflows, conflict resolution, and worktree management.
conventional-commit
Generer conventional commit-meldinger med Nav-relevante scopes og breaking change-format.
commit-changes
Stage, commit, and amend changes with conventional commit messages. Covers reviewing changes, selective staging, writing descriptive commit messages using HEREDOC format, and verifying commit history. Use when saving a logical unit of work to version control, creating a commit with a conventional message, amending the…
configure-git-repository
Configure a Git repository with proper .gitignore, branch strategy, commit conventions, hooks, and remote setup. Covers initial setup and common patterns for R, Node.js, and Python projects. Use when initializing version control for a new project, adding a .gitignore for a specific language or framework, setting up…
git-commit
Safely create a git commit by validating repository state, staging intended changes, scanning for secrets/conflicts, generating a Conventional Commits message (repository convention first, else an English Angular default) from the staged diff, and committing without amend.