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 agentmods add skills/friedbotstudio/baseline/archivenpx skills add friedbotstudio/baseline --skill archivegit clone --depth 1 https://github.com/friedbotstudio/baselineWhat 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 | $0.00077 | $0.02887 |
| Opus 5 | $0.00039 | $0.01443 |
| Sonnet 5 | $0.00015 | $0.00577 |
| Haiku 4.5 | $0.00008 | $0.00289 |
Grade A, and why
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 2d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
archive — Phase 10.5
Invoked after /document and before /commit. Pillar 4 of seed.md ("no historical data — moved to archive") happens here.
The archival bundle is planned at spec time — the spec's slug determines which files travel together. This skill is the executor.
Prereq
workflow.json must have document in completed OR in exceptions. Otherwise stop and say which phase is missing.
Steps
-
Read
.claude/state/workflow.jsonto get the slug (derive fromrequest, or from anydocs/specs/*.mdthat was produced — whichever is present). -
Render the per-phase timing table FIRST (before the move, while the consent tokens are still in
.claude/state/):node .claude/hooks/lib/timing.mjs render <slug>It reads the
phase_timerstamps at.claude/state/timing/<slug>.jsonlplus consent-token mtimes (spec_approvals/<slug>.approval,commit_consent) and writes a per-phase model-time-vs-human-wait table to<bundle>/timing.md. The table is born in the bundle (it creates the bundle dir). It must run before Step 4 because the archive script movesspec_approvals/<slug>.approvalinto the bundle — render it first or the approve-direction gate's human-wait readsn/a. Best-effort — a missing/sparse timing log yields a header-only table, never an error. -
Verify the spec's declared delta against the landed diff with
verifyAndApplyDelta, then apply only what it confirms (gated bymemory.architecture_map.enabled; skip the whole of Steps 3 and 5.5 when false). This is what keepsdocs/system/true to what is on disk instead of drifting the moment the next cycle ships.It must run before Step 4, for the same reason Step 2 does.
archive.shmovesdocs/specs/<slug>.mdinto the bundle; after thatresolveSpecPathreturnsnull, the## System deltatable is never read, and every array below comes back empty — which is byte-identical to a spec that declared nothing. Verify first, or a real drift archives silently green. ThespecMissingfield exists to make that failure loud if the order is ever changed back: when it istrue, the empty arrays mean the table was not read, not the table was clean.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 121 lines · 77 tokens per session scan A 47ce62481be3
archive is a skill published in the GitHub repository friedbotstudio/baseline (11 stars, last pushed 6d ago), licensed Apache-2.0. It adds 77 tokens to every session and 2,887 once invoked, about $0.0004 per session on Opus 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 2026-08-30.
Other skills, from other repositories
dev-standards
Enforces development workflows, quality gates, coding standards, and release processes for the deterministic-agent-control-protocol project. Use when implementing features, fixing bugs, refactoring architecture, adding integrations, updating policies, writing tests, updating documentation, or preparing releases.
code-review-with-lsp
Code review with LSP-powered code intelligence. Uses MCP tools (diagnostics, hover, references, definition, symbols) for semantic code understanding, not just text grep.
i18n-check
国际化完整性检查。检查翻译 key 是否缺失、硬编码文本、locale 文件一致性。.
vue-best-practices
Vue 2/3 代码规范检查。包括组件命名、Props 校验、Composition API 规范等。.
python-review
Python 遗留代码审查：bare except、SQL 注入、反序列化、密钥、调试输出.
rust-review
Rust 服务审查：panic、SQL 注入、密钥、错误吞没、遗留标记.