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 commands/yibie/spec-agents.md/migrate-v3git clone --depth 1 https://github.com/yibie/SPEC-AGENTS.mdWrote 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/yibie/spec-agents.md/migrate-v3)<a href="https://agentmods.dev/commands/yibie/spec-agents.md/migrate-v3"><img src="https://agentmods.dev/badge/commands/yibie/spec-agents.md/migrate-v3.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 | $0.00019 | $0.00711 |
| Opus 5 | $0.00010 | $0.00356 |
| Sonnet 5 | $0.00004 | $0.00142 |
| Haiku 4.5 | $0.00002 | $0.00071 |
Grade A, and why
migrate-v3 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/migrate-v3 — Migrate Legacy SPEC-AGENTS Projects
Use this command when a project already has the old static SPEC-AGENTS layout:
.phrase/phases/
phase-*/
spec_*
plan_*
task_*
change_*
issue_*
The migration goal is not to convert every old file into a new format. The goal is to archive historical detail, rebuild the active context, and promote only decision-relevant material into v3.
Target Structure
.phrase/
decision.md
roadmap.md
current.md
evidence.md
archive/
legacy-v2/
Steps
-
Inventory legacy material. List existing
.phrase/phases/, oldspec_*,plan_*,task_*,change_*,issue_*,adr_*, andtech-refer_*files. -
Create v3 files if missing. Ensure these files exist:
.phrase/decision.md .phrase/roadmap.md .phrase/current.md .phrase/evidence.md .phrase/archive/ -
Archive old phase material. Move completed, stale, or legacy phase directories under:
.phrase/archive/legacy-v2/Do not delete old material during migration unless the user explicitly asks.
-
Promote durable rules. Extract long-lived constraints from old
adr_*,tech-refer_*, and project notes into.phrase/decision.md,.phrase/adr/, or.phrase/protocol/. -
Compress roadmap. Extract phase-level direction from old
plan_*or phase indexes into.phrase/roadmap.md. Do not copy detailed task lists. -
Rebuild current context. Extract only the active phase into
.phrase/current.md:- goal
- entry condition
- scope
- out of scope
- acceptance gate
- active task slice
- verification plan
- known blockers
-
Promote evidence. Extract only decision-relevant facts into
.phrase/evidence.md:- unresolved blockers
- verified results
- failed assumptions
- rejected paths
- next phase recommendation
-
Write cutover note. Add an evidence entry named
v3 migration cutoverthat records where old material was archived and which files now define active context.
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 · 120 lines · 19 tokens per session scan A 5cd6817be4ce
migrate-v3 is a command published in the GitHub repository yibie/SPEC-AGENTS.md (126 stars, last pushed 4d ago), licensed MIT. It adds 19 tokens to every session and 711 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.