Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/stn1slv/spec-kit-archive/archive)<a href="https://agentmods.dev/commands/stn1slv/spec-kit-archive/archive"><img src="https://agentmods.dev/badge/commands/stn1slv/spec-kit-archive/archive.svg" alt="Measured on agentmods" 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 | $0.00015 | $0.32760 |
| Opus 5 | $0.00008 | $0.16380 |
| Sonnet 5 | $0.00003 | $0.06552 |
| Haiku 4.5 | $0.00002 | $0.03276 |
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 6d 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 — 934 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Act as the Chief Software Architect and Documentation Maintainer.
A feature has been merged into the main branch. Your goal is to archive the feature specification into the main project memory — ensuring completeness, resolving conflicts, closing gaps, and respecting the project constitution.
Completeness means nothing is lost from the feature's own artifacts. It does not mean filling gaps from elsewhere. See Allowed Sources below, which bounds every step of this command.
User Input
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty).
Input Parsing
This command archives exactly one feature per run. There is no batch or range mode. To archive several features, run the command once per feature in ascending feature order, so each run sees the result of the one before it.
Parse $ARGUMENTS as follows:
- First token: feature spec directory path. Spec-kit projects name these directories in more than one way, and all of them are valid here: sequential (
specs/007-invoice-settings), timestamped (specs/20260814-101500-invoice-settings, produced byspecifywith timestamp numbering), and nested under a scope directory (specs/billing/006-invoice-settings). Nothing in this command may key on a three-digit prefix. - Then: scope modifiers (optional,
--flags immediately after the path), followed by optional free-form guidance text
Supported scope modifiers (if none provided, update all artifacts):
--spec-only— update only.specify/memory/spec.md--plan-only— update only.specify/memory/plan.md--changelog-only— update only.specify/memory/changelog.md--agent-only— update only the agent context file(s), as discovered by Step 0.7; when a project keeps several in sync, this covers all of them
If several scope modifiers are supplied, the scope is their union — --spec-only --changelog-only updates both spec.md and changelog.md and nothing else. "Only" bounds the whole set, not each flag individually.
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.
- 6d ago First seen · 934 lines · 15 tokens per session scan A c01cdc6e748a
archive is a command published in the GitHub repository stn1slv/spec-kit-archive (29 stars, last pushed 11d ago), licensed MIT. It adds 15 tokens to every session and 32,760 once invoked, about $0.0001 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 commands, from other repositories
speckit.harness.init
Initialize externalized harness state (budget, candidates, curated set, evidence, verification, observations) for the active feature.
speckit.harness.explore
Run a budget-aware exploration loop that externalizes every finding into the harness state files.
speckit.harness.report
Synthesize curated evidence and verification records into the feature's research.md with a coverage table.
speckit.harness.status
Render a compact, budget-aware slice of the harness state with a recommended next action.
speckit.harness.verify
Adversarially verify claims in spec/plan artifacts against primary sources and record verdicts.
reference
All five commands are prompt files in commands/, registered in extension.yml. Each resolves HARNESSDIR the same way: config file → SPECKITHARNESS env vars → arguments; feature directory from the current git branch (e.g. branch 003-user-auth → specs/003-user-auth/), else the most recently modified directory under…