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 PetriLahdelma/project-spine --skill project-spine-workspacegit clone --depth 1 https://github.com/PetriLahdelma/project-spineWrote 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/petrilahdelma/project-spine/project-spine-workspace)<a href="https://agentmods.dev/skills/petrilahdelma/project-spine/project-spine-workspace"><img src="https://agentmods.dev/badge/skills/petrilahdelma/project-spine/project-spine-workspace/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/petrilahdelma/project-spine/project-spine-workspace"><img src="https://agentmods.dev/badge/skills/petrilahdelma/project-spine/project-spine-workspace.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00055 | $0.00471 |
| Opus 5 | $0.00028 | $0.00235 |
| Sonnet 5 | $0.00011 | $0.00094 |
| Haiku 4.5 | $0.00006 | $0.00047 |
Grade A, and why
project-spine-workspace 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 11d 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.
What it actually says
Hosted workspace guardrail
Goal: prevent agents from inventing or invoking hosted workspace flows that are not routed in the public OSS CLI.
Current status
The public Project Spine CLI is OSS-first and local-first. Its routed commands are:
spine init
spine compile
spine inspect
spine export
spine template list|show|save
spine explain
spine drift check|diff
spine tokens pull
spine doctor
Hosted workspace commands are dormant in source but intentionally not exposed from spine --help. Do not instruct users to run:
spine loginspine logoutspine whoamispine workspace ...spine publish ...spine rationale ...spine drift check --pushspine template pullspine template list --workspace
What to recommend instead
For team sharing today:
- Commit project-local templates under
./.project-spine-templates/<name>/. - Save personal reusable templates with
spine template save --location user. - Share generated
AGENTS.md,CLAUDE.md,.github/copilot-instructions.md,.cursor/rules/project-spine.mdc, and.project-spine/exports/*through normal version control. - Use
spine drift check --fail-on anyin CI without--push.
For client-facing summaries:
- Review
.project-spine/exports/rationale.mdlocally. - Share it through the user's existing docs, email, or client portal workflow.
If the user insists on hosted workspaces
Be explicit:
Hosted workspace code exists in the repository, but it is not part of the public CLI surface right now. The OSS launch is intentionally local-first. Use project-local templates and CI drift checks until a hosted workspace release is intentionally routed and documented.
Then continue with the local workflow that gets them closest to their goal.
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.
- 11d ago First seen · 59 lines · 55 tokens per session scan A a9b769ff34d8
project-spine-workspace is a skill published in the GitHub repository PetriLahdelma/project-spine (2 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 471 once invoked, about $0.0003 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
create-issue
Draft and submit a GitHub issue from a user idea or bug description, with bilingual body and correct labels.
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
swarm-plan
Full execution protocol for MODE: PLAN -- plan creation, external plan ingestion, QA gate persistence, task granularity, and traceability checks.
loop
Full execution protocol for MODE: LOOP — the compound-engineering loop: brainstorm → plan → build → review → improve, iterating under defense-in-depth stop conditions with generator/critic separation, durable resumable state, and mandatory compounding learning capture. Loaded on demand by the architect when the loop…