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 skills/saitarrun/devforge-ai/intent-clarificationnpx skills add saitarrun/Devforge-ai --skill intent-clarificationgit clone --depth 1 https://github.com/saitarrun/Devforge-aiWrote 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/saitarrun/devforge-ai/intent-clarification)<a href="https://agentmods.dev/skills/saitarrun/devforge-ai/intent-clarification"><img src="https://agentmods.dev/badge/skills/saitarrun/devforge-ai/intent-clarification.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 | $0.00033 | $0.00605 |
| Opus 5 | $0.00016 | $0.00302 |
| Sonnet 5 | $0.00007 | $0.00121 |
| Haiku 4.5 | $0.00003 | $0.00060 |
Grade A, and why
intent-clarification 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 4d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Intent Comprehension & Goal Alignment Skill
This skill guides agents to accurately decipher what the user actually needs versus what they literally asked for, preventing misalignment before code is written.
1. Intent Deconstruction Framework (The 4-Layer Lens)
Whenever a user provides a prompt or feature request, analyze it through four concentric layers:
[Layer 1: Literal Request] → "Add a login screen"
↓
[Layer 2: Underlying Objective] → User needs secure session management and user identification
↓
[Layer 3: Latent Requirements] → Password reset, OAuth/SSO, session invalidation, CSRF protection
↓
[Layer 4: Non-Functional Drivers]→ Enterprise compliance, low latency, zero-downtime migration
2. Ambiguity Detection & Resolution Matrix
If a prompt contains ambiguous or high-entropy phrasing, immediately classify and address the gap:
| Ambiguity Pattern | Example User Phrasing | Resolution Action |
|---|---|---|
| Vague Scope | "Make it faster", "Make it look modern" | Quantify targets: Ask for specific p95 latency targets (e.g. <100ms) or UI design references. |
| Architectural Ambiguity | "Connect to external data" | Determine sync vs async (Webhook vs Polling vs Kafka) and error retry semantics. |
| Missing Failure Modes | "Send email when user signs up" | Clarify transactional reliability: Should signup fail if the email provider is down? |
| Implicit Authorization | "Admins can manage team members" | Ask if roles are static or configurable (RBAC vs ABAC). |
3. High-Fidelity Confirmation Protocol
When clarifying intent with the user:
- Replay Understandings with Options: Present the extracted mental model back in plain language with concrete trade-offs.
- Proactively Suggest Industry Defaults: Never present open-ended confusion; provide a solid (Recommended) option.
- Check for Unintended Side-Effects: State potential impacts on existing workflows (e.g., "Note: Enabling MFA will require updating the mobile login flow").
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.
- 4d ago First seen · 56 lines · 33 tokens per session scan A ab8729e62bbe
intent-clarification is a skill published in the GitHub repository saitarrun/Devforge-ai (5 stars, last pushed 21d ago), licensed Apache-2.0. It adds 33 tokens to every session and 605 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 2026-08-31.
Other skills, from other repositories
evolve
Research-driven multi-cycle improvement director. Forms causal hypotheses about why scores are low, validates them with scout agents before attacking, dispatches axis-parallel fleet attacks, extracts transferable patterns, and runs indefinitely within a budget envelope. Accumulates a persistent belief model and…
improve
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
research
Focused research investigations. Converts questions into structured findings with confidence levels and source citations. Single agent by default; with --parallel (or when the question decomposes into 3+ independent angles) it spawns scout agents whose findings are compressed into a unified brief. Does not make…
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.
qa
Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).