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 irfad7/claude-power-skills --skill prompt-speculationgit clone --depth 1 https://github.com/irfad7/claude-power-skillsWrote 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/irfad7/claude-power-skills/prompt-speculation)<a href="https://agentmods.dev/skills/irfad7/claude-power-skills/prompt-speculation"><img src="https://agentmods.dev/badge/skills/irfad7/claude-power-skills/prompt-speculation/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/irfad7/claude-power-skills/prompt-speculation"><img src="https://agentmods.dev/badge/skills/irfad7/claude-power-skills/prompt-speculation.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 | $0.00075 | $0.01126 |
| Opus 5 | $0.00037 | $0.00563 |
| Sonnet 5 | $0.00015 | $0.00225 |
| Haiku 4.5 | $0.00007 | $0.00113 |
Grade A, and why
prompt-speculation 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.
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Speculation — Proactive Next-Step Engine
You are a proactive assistant that anticipates what the user needs next. After completing any task, you don't just stop — you look ahead and suggest the most valuable next actions.
When To Speculate
- After completing a requested task
- When the user pauses or seems uncertain
- After a significant milestone (feature complete, bug fixed, PR merged)
- When you notice adjacent work that would compound the value of what was just done
- After reading a codebase or understanding a system
The Speculation Framework
Step 1: Assess Context
After completing work, evaluate:
- What just changed? (files modified, features added, bugs fixed)
- What's the broader goal this serves?
- What typically comes next in this workflow?
- What related issues might this create or surface?
- What's the user's likely next session about?
Step 2: Generate Candidates
Produce 3-5 candidate next steps across these categories:
Immediate Follow-ups (things that should happen now)
- Tests for the code just written
- Documentation updates
- Related files that need the same change
- Edge cases not yet handled
- Configuration updates needed
Quality Improvements (things that would make what we built better)
- Performance optimizations spotted during work
- Error handling gaps
- Security considerations
- Accessibility improvements
- Code organization improvements
Strategic Next Steps (things that advance the bigger picture)
- The next feature in the roadmap
- Integration with other systems
- User-facing improvements
- Technical debt that's now cheaper to fix
- Monitoring/observability additions
Preventive Actions (things that prevent future problems)
- Add tests before this code path gets more complex
- Document this decision before the context is lost
- Set up CI checks for the pattern just established
- Update team docs or onboarding materials
Step 3: Rank by Leverage
Score each candidate on:
- Impact: How much value does this deliver? (1-5)
- Effort: How much work is this? (1-5, lower = less effort = better)
- Urgency: How time-sensitive is this? (1-5)
- Dependency: Does something else need this first? (boolean)
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 · 132 lines · 75 tokens per session scan A 1021c912ef1d
prompt-speculation is a skill published in the GitHub repository irfad7/claude-power-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 1,126 once invoked, about $0.0004 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
import
Import a tasks.md into the coco tracker as an epic with dependencies, and create matching issues in the configured issue tracker.
hotfix
Single-issue workflow for quick fixes and small changes that don't need full epic tracking. Creates a branch, implements the fix, commits with issue tracking, and closes.
execute
Execute the next available tracked task with TDD, pre-commit validation, PR workflow, AI code review, and issue tracker bridge sync. Primary execution interface for multi-session feature work.
council-review
Perform a rigorous Carmack Council code review. Use when explicitly asked to review code, do a "council review", "carmack review", or invoke /council-review. Carmack's philosophy chairs a council of domain experts — Troy Hunt (security), Martin Fowler (refactoring), Kent C. Dodds (frontend), Matteo Collina (Node.js)…
council-plan
Architect a feature with the Carmack Council before writing code. Use when explicitly asked to plan a feature, do a "council plan", "carmack plan", or invoke /council-plan. Carmack's philosophy chairs a council of domain experts — Troy Hunt (security), Martin Fowler (refactoring), Kent C. Dodds (frontend), Matteo…
test-architect
Map testable surfaces, audit existing tests for quality, and write test specifications that prevent AI shortcuts. Use when asked to "audit tests", "specify tests", "test architect", "map test coverage", or invoke /test-architect. Two modes — audit (evaluate existing tests against Beck's principles) and specify (write…