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/requirementsnpx skills add saitarrun/Devforge-ai --skill requirementsgit 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/requirements)<a href="https://agentmods.dev/skills/saitarrun/devforge-ai/requirements"><img src="https://agentmods.dev/badge/skills/saitarrun/devforge-ai/requirements.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 | $0.00079 | $0.00701 |
| Opus 5 | $0.00039 | $0.00351 |
| Sonnet 5 | $0.00016 | $0.00140 |
| Haiku 4.5 | $0.00008 | $0.00070 |
Grade A, and why
requirements 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.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Requirements & User Stories (INVEST)
INVEST Criteria — Making Stories Actionable
A well-written user story is INVEST-compliant:
- Independent: Story doesn't depend on another story (can be built in any order)
- Negotiable: Details can be discussed and refined (not cast in stone)
- Valuable: Delivers value to the end user (not just internal plumbing)
- Estimable: Engineer can estimate size (2-13 story points)
- Small: Fits in a single sprint (1-2 weeks max)
- Testable: Acceptance criteria are clear and provable
Story Format
## User Story: [Feature Name]
As a [role/persona]
I want to [action/capability]
So that [business value/outcome]
### Acceptance Criteria
- Given [precondition]
When [action]
Then [observable result]
### Edge Cases & Questions
- Q: What happens if [scenario]?
- Q: Should we support [case]?
### Definition of Done
- [ ] Code written and reviewed
- [ ] Acceptance criteria tests pass
- [ ] Documentation updated
- [ ] Performance tested (if relevant)
- [ ] Security review passed (if relevant)
Story Estimation
- Small (2-3 pts): Can be done in a day, low complexity, well-understood
- Medium (5 pts): Takes 2-3 days, some unknowns, requires design
- Large (8 pts): Takes full sprint, many unknowns, high risk
- Too Large (13+ pts): Break into smaller stories
Common Pitfalls
| Pitfall | Bad Example | Good Example |
|---|---|---|
| Not independent | "Add payment form" depends on "Add payment backend" | "Add payment form UI" + "Add payment API" (can be mocked) |
| Not valuable | "Refactor database layer" | "Enable payments via Stripe" |
| Not testable | "Code should be fast" | "Page load <2 seconds on 3G" |
| Too large | "Build entire user profile system" | "User can upload profile photo" |
| Unclear | "Handle edge cases" | "Given missing email, show validation error" |
Ambiguity Detection
Always ask these questions before starting work:
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 · 74 lines · 79 tokens per session scan A 47973ce0eb88
requirements is a skill published in the GitHub repository saitarrun/Devforge-ai (5 stars, last pushed 22d ago), licensed Apache-2.0. It adds 79 tokens to every session and 701 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 2026-09-03.
Other skills, from other repositories
merge-review
Reviews pending fleet worktree merges before they're accepted. Reads the merge-check queue, detects file-level conflicts between branches, proposes a safe merge order, and surfaces reconciliation plans for overlapping changes.
workspace
Multi-repo campaign coordinator. Same lifecycle as fleet -- scope claims, discovery relay, wave-based execution -- but the unit of work is a repo, not a file. Coordinates campaigns across repositories with shared context.
decision-map
Turn a loose idea into a git-tracked, session-resumable map of typed investigation tickets, then drive them to resolution one at a time. The planning-loop engine for work that is still being figured out — too fuzzy for a campaign, too big for a single intake item. Resolved tickets graduate into .planning/intake/ for…
unharness
Safely leave Citadel using the active adoption receipt. Produces a no-write, reviewable plan, preserves a portable archive, removes only exact owned material, and reports modified or externally registered surfaces as retained or unknown. Legacy installs must be imported before exact leave is claimed.
orient
Orient a spec-driven jig/servo/shaper repository with a read-only, project-wide briefing: start from the workflow.py orient headline, then survey open pull requests and unmerged work, Proposed ADRs, DEFERRED triggers, refinement items, release plans, the inbox, and the bug board; render one readable headline, titled…
process-backlog
Internal crew primitive, dispatched by /crew:run — do not invoke directly or select it for a user request; route backlog/catch-up requests to /crew:run, which decides the full workflow. (Function: find and advance stalled issues/PRs or ledger tasks, bounded; never merges.).