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 rules/snowdreamtech/template/speckit_speckit.tasksgit clone --depth 1 https://github.com/snowdreamtech/templateWhat 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 | $0.00000 | $0.00061 |
| Opus 5 | $0.00000 | $0.00030 |
| Sonnet 5 | $0.00000 | $0.00012 |
| Haiku 4.5 | $0.00000 | $0.00006 |
Grade A, and why
speckit_speckit.tasks 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 yesterday.
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
Speckit Workflow: speckit.tasks
When the user asks to run /speckit.tasks, you MUST read .specify/commands/speckit.tasks.md and follow its instructions exactly.
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.
- yesterday First seen · 9 lines · 61 tokens per session scan A 8fa6aef49fda
speckit_speckit.tasks is a cursor rule published in the GitHub repository snowdreamtech/template (15 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 61 tokens. 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 2026-09-01.
Other cursor rules, from other repositories
agent-routing.keepalive-wake
🔒 LOCKED — managed by clade Source: rules/core/agent-routing.keepalive-wake.md Edit at: $CLADEHOME Local edits will be reverted by the next sync. -->.
agent-routing.pi-input-intercept
Codex 模型經 Pi machine dispatch 提出問題時的攔截、評估、代答或升級 protocol；觸及 spectra change / screenshot 情境時 path-scoped 載入.
code-doc-lockstep
Binding — code changes must update matching docs (architecture / feature / API / runbook / SDD) in the same diff.
completion-time-self-audit
Self-audit before claiming work is complete (no defer / follow-up / mock).
sdd-workflow
Mandatory development workflow (Plan + Todo + SDD pipeline).
go-conventions
Go conventions for all Go code (modules, naming, errors, logging, metrics).