Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add pitimon/8-habit-ai-dev/plugin install 8-habit-ai-devWrote 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/pitimon/8-habit-ai-dev/save-spec)<a href="https://agentmods.dev/skills/pitimon/8-habit-ai-dev/save-spec"><img src="https://agentmods.dev/badge/skills/pitimon/8-habit-ai-dev/save-spec.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 | $0.00098 | $0.03068 |
| Opus 5 | $0.00049 | $0.01534 |
| Sonnet 5 | $0.00020 | $0.00614 |
| Haiku 4.5 | $0.00010 | $0.00307 |
Grade A, and why
save-spec 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scaffold Project SPEC.md (/save-spec)
Habits: H8 (Find Your Voice — pick the deployment mode that fits your repo) + H2 (Begin with End in Mind — establish the save point on day 1) | Anti-pattern: Copying the SPEC.md template by hand every time you start a new operational repo, then forgetting to fill the timestamp.
When to Use
- The repo fits the project-orientation hub mode (operational / infra / integration / single-system) — not the per-feature
--persist <slug>mode. - You want a one-page digest at the project root that points to project-specific detail files and acts as the read-first save point after
/clearor/compact. - No
SPEC.mdexists yet at the project root. - See
guides/spec-digest-pattern.mdfor the full pattern. This skill scaffolds the file; the discipline of maintaining it is yours.
When to Skip
- Repo uses the feature-spec mode (
docs/specs/<slug>/{prd,design,tasks,current-state}.md). Use/requirements --persist,/design --persist,/breakdown --persistinstead. SPEC.mdalready exists at the project root — Phase 1 is generator-only; edit it manually or wait for Phase 2--update.- One-off scripts / single-file repos where a digest adds no value.
- Memory-MCP already active (
claude-mem,memforge, or equivalent with SessionStart context injection) AND your existingCLAUDE.mdis short enough to scan in <30 seconds (a ~150-line threshold is a reasonable rule of thumb). In that combination, §1 (architecture) is already covered byCLAUDE.md's top section and §4 (Current state save-point) is already covered by the memory-MCP's chronological injection — more faithfully than a human-curated §4, because the memory layer captures what actually happened in the last session, not what the operator remembered to write down. §4 is the only section providing net value over what you already have; consider writing a short## Current statesection directly intoCLAUDE.mdinstead of scaffolding a separate file. (Surfaced by Adopter #2's third-repo dogfood — issue #207. The skill's H8 Checkpoint already acknowledges "the value depends on the user's habit of updating it" — this skip entry extends that honesty to the upstream question of whether the scaffold is worth maintaining at all.)
What ships with it
1 file 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.
- 6d ago First seen · 106 lines · 98 tokens per session scan A 29ee219e2faa
save-spec is a skill published in the GitHub repository pitimon/8-habit-ai-dev (3 stars, last pushed 1mo ago), licensed MIT. It adds 98 tokens to every session and 3,068 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
brainstorm
Interactive idea maturation — explore, research, shape raw ideas into actionable plans. Use when you have a rough idea and want to think it through.
challenge
Adversarial review — Fable 5 stress-tests reasoning, Gemini checks knowledge. Use before plan or architecture decisions.
review
Business review — weekly health check, monthly close, or ad-hoc audit. Subcommands: weekly, monthly, check. Use for periodic reviews or metrics assessment.
nextjs-patterns
Next.js App Router — Server Components, Actions, streaming, caching. Use when building or migrating Next.js apps.
sitrep
Situational awareness — where am I, what was I doing, what's next. Context recovery after compression, confusion, or mid-session reorientation.
fastapi
FastAPI best practices + Pydantic. Use when building or reviewing FastAPI APIs.