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 AnkitClassicVision/ankit_shared_skills --skill run-projectgit clone --depth 1 https://github.com/AnkitClassicVision/ankit_shared_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/ankitclassicvision/ankit_shared_skills/run-project)<a href="https://agentmods.dev/skills/ankitclassicvision/ankit_shared_skills/run-project"><img src="https://agentmods.dev/badge/skills/ankitclassicvision/ankit_shared_skills/run-project.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 5.1 | $0.00019 | $0.03799 |
| Opus 5 | $0.00010 | $0.01899 |
| Sonnet 5 | $0.00004 | $0.00760 |
| Haiku 4.5 | $0.00002 | $0.00380 |
Grade A, and why
run-project 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 7d 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 — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/run-project
Invocation
/run-project [path]
path: Repo path (defaults to current directory)- That's it. No flags. The skill decides the rest.
What It Does
Runs any repo through a pipeline that produces a spec-backed, issue-tracker-ready implementation plan.
Self-contained public bundle
This public bundle is intended to be installed as a set. If the repository folders are copied together into a skills directory, /run-project has all named planning and artifact dependencies locally: grill-me, to-prd, agent-spec-writer, context-layer-generator, seeit, to-issues, writing-plans, handoff, skillify, codebase-organizer, improve-codebase-architecture, aac-process-design, and agenttwin.
The only external dependency is the user's runtime executor: a local coding agent, shell/test runner, or human operator for implementation.
Blind evals are generated after every artifact phase and hidden until execution QA.
Grill → PRD → [Blind Eval] → Agent Spec → [Blind Eval] → Context Layer → [Blind Eval]
→ SEEIT → To-Issues → [Blind Eval] → Writing-Plans → [Blind Eval]
→ Execute (all evals revealed to QA) → Accept
Auto-Detection (No Flags Needed)
| Decision | How It Decides |
|---|---|
| AAC pre-phase? | Sees "agent", "workflow", "automation", "bot", "RAG", "LLM pipeline" in intent or finds agent_registry, aac-v2, agenttwin files → runs AAC. Otherwise skips. |
| Brownfield deepening? | Repo exists + >1000 LOC → auto-runs codebase analysis during Grill. Presents findings. User says yes/no. |
| QA checks? | Finds tests → runs them. Finds lint config → runs it. No config → skips. |
| Resume? | Finds .run-project/state.json → asks "Resume from Phase N?" One yes/no. |
| Surface dispatch? | Detects Hermes vs Claude Code vs Codex automatically. |
Human Gates (Two Only)
- After Grill — "Good to write the PRD?" (yes/no)
- After SEEIT — "Looks right? Proceed to issues?" (yes/no)
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/agentic-packet-first-seeit.md 2.5 KB
- references/blind-eval-mechanism.md 6.1 KB
- references/codex-cli-handoff.md 1.3 KB
- references/execution-pitfalls.md 4.3 KB
- references/fresh-restart-existing-run-project.md 2.0 KB
- references/pipeline.md 6.1 KB
- references/seeit-deployment.md 926 B
- scripts/detect-project-type.py 5.4 KB runs code
- scripts/organize-code.py 19 KB runs code
- scripts/qa-loop.py 20 KB runs code
- scripts/resume-state.py 6.1 KB runs code
- templates/handoff-template.md 457 B
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.
- 7d ago First seen · 322 lines · 19 tokens per session scan A 84d66015eb80
run-project is a skill published in the GitHub repository AnkitClassicVision/ankit_shared_skills (11 stars, last pushed 26d ago), licensed MIT. It adds 19 tokens to every session and 3,799 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
github-triage
Unified GitHub triage for issues AND PRs. Classifies open items, answers questions from codebase, analyzes bugs, reviews PRs, and produces a structured triage report. Triggers: 'triage', 'triage issues', 'triage PRs', 'github triage'.
issue-report-generator
Automatically generate clear, actionable issue reports from failing tests and repository analysis. Analyze test failures to understand expected vs. actual behavior, identify affected code components, and produce well-structured Markdown reports suitable for GitHub Issues or similar trackers. Use when a test fails…
python-repo-quickstart
Quickly analyzes Python repositories to understand their purpose, structure, and setup requirements. Use when Claude needs to onboard to a new Python codebase, understand project structure, identify entry points, determine dependencies, or generate setup instructions. Trigger when users ask to "analyze this Python…
readme-generator
Generate comprehensive, user-friendly README.md files for code repositories. Use when creating documentation for new projects, updating existing READMEs, or improving project onboarding. Produces READMEs with project introduction, prerequisites, environment setup, executable usage instructions, and repository…
agentdesk
Initialize, consult on, operate, validate, and recover task-card-driven multi-agent software projects. Use when Codex needs a bounded multi-session roundtable for a complex topic, product, architecture, risk, or requirements question—including a topic outside a repository—or needs to scaffold or upgrade a repository…
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.