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 marconae/speq-skill --skill speq-spec-mergegit clone --depth 1 https://github.com/marconae/speq-skillWrote 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/marconae/speq-skill/speq-spec-merge)<a href="https://agentmods.dev/skills/marconae/speq-skill/speq-spec-merge"><img src="https://agentmods.dev/badge/skills/marconae/speq-skill/speq-spec-merge/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/marconae/speq-skill/speq-spec-merge"><img src="https://agentmods.dev/badge/skills/marconae/speq-skill/speq-spec-merge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00034 | $0.00951 |
| Opus 5 | $0.00017 | $0.00476 |
| Sonnet 5 | $0.00007 | $0.00190 |
| Haiku 4.5 | $0.00003 | $0.00095 |
Grade A, and why
speq-spec-merge 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Merge
Load Plan Context
Read: specs/_plans/<plan-name>/plan.md
List: specs/_plans/<plan-name>/**/spec.md
Run speq feature list to see the current permanent spec library.
Apply Deltas
For each delta spec at specs/_plans/<plan-name>/<domain>/<feature>/spec.md:
specs/<domain>/<feature>/spec.md exists?
├─ No → Copy delta (strip markers)
└─ Yes → Merge using markers below
| Marker | Action |
|---|---|
DELTA:NEW |
Append scenario |
DELTA:CHANGED |
Replace scenario with same name |
DELTA:REMOVED |
Delete scenario with same name |
After each merge:
- Strip all
<!-- DELTA:* -->markers - Validate:
speq feature validate <domain>/<feature> - If validation fails, stop and report. Do not guess fixes
Check Library Thresholds
After all merges:
| Metric | Threshold | Action |
|---|---|---|
| Scenarios per spec | >10 | Return to orchestrator for user decision |
| Domain features | >8 | Return to orchestrator for user decision |
Never assume: library reorganization is a user decision. Return a concrete question to the orchestrator.
Promote ADRs to Permanent Decision Log
Read specs/_plans/<plan-name>/decision-log.md (if it exists).
For each entry where Promotes to ADR: yes:
-
Convert to ADR format using
/speq-plan'sreferences/decision-log-permanent-template.md:- Title — from the decision entry heading
- ID — a kebab-case slug derived from the title; MUST be unique across every file in
specs/_decision/ - Plan —
<plan-name> - Status —
Accepted - Supersedes (optional) — if the entry names an earlier decision it replaces, set this to that decision's existing ADR slug
- Context — synthesized from the entry's Rationale + Alternatives
- Decision — from the entry's Decision bullet
- Options Considered — from the entry's Alternatives bullet
- Consequences — brief inference from Rationale
-
Write ONE new fragment file
specs/_decision/NNN-<plan-name>.md:- NNN = (count of existing files in
specs/_decision/) + 1, zero-padded to 3 digits - H1:
# Decisions: <plan-name> - Emit one
## ADR: <Title>block per promoted entry, in decision-log order - MUST NOT edit any other file in
specs/_decision/— a supersede reference is a one-way pointer from the new ADR's**Supersedes:**field to the target slug
- NNN = (count of existing files in
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 Changed · +1 lines a4b3e4e57f0e
- 12d ago First seen · 91 lines · 34 tokens per session scan A 433c496a21be
speq-spec-merge is a skill published in the GitHub repository marconae/speq-skill (50 stars, last pushed 6d ago), licensed MIT. It adds 34 tokens to every session and 951 once invoked, about $0.0002 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
build-executor
Govern implementation from an approved execution contract. Invoke when execution-contract.md is approved and the user wants disciplined build work, TDD execution, or guarded batch-by-batch implementation.
workflow-start
Primary entry point for the spec-superflow state-machine workflow. Invoke when the user is inside an active spec-superflow change directory (look for .spec-superflow.yaml, changes/ /, proposal.md, specs/, design.md, tasks.md, or execution-contract.md) and asks to start, continue, resume, implement, plan, or figure out…
bug-investigator
Use when encountering any bug, test failure, or unexpected behavior during spec-superflow execution, before proposing fixes. Invoked automatically when build-executor hits a blockage.
release-archivist
Close out a spec-superflow change with verification, summary, and archive readiness. Invoke when implementation is complete, verification is underway, or the user asks for a final wrap-up.
contract-builder
Convert approved planning artifacts into an execution contract. Invoke when the user wants to start building, asks to move from planning to implementation, or when execution-contract.md is missing or stale.
need-explorer
Clarify intent, scope, constraints, and success criteria before artifact creation. Invoke when the request is fuzzy, the user is comparing options, or the workflow needs a stable change definition before writing artifacts.