Borrowing it
Nothing to install: this file belongs to dradoaica/cogov-a-sdlc. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dradoaica/cogov-a-sdlc/main/.agents/skills/ponytail/SKILL.mdgit clone --depth 1 https://github.com/dradoaica/cogov-a-sdlcWrote 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/dradoaica/cogov-a-sdlc/ponytail)<a href="https://agentmods.dev/skills/dradoaica/cogov-a-sdlc/ponytail"><img src="https://agentmods.dev/badge/skills/dradoaica/cogov-a-sdlc/ponytail/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/dradoaica/cogov-a-sdlc/ponytail"><img src="https://agentmods.dev/badge/skills/dradoaica/cogov-a-sdlc/ponytail.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 | $0.00091 | $0.01123 |
| Opus 5.5 | $0.00036 | $0.00449 |
| Sonnet 5.5 | $0.00018 | $0.00225 |
| Haiku 4.5 | $0.00009 | $0.00112 |
Grade A, and why
ponytail 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 8d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Ponytail (Pragmatic Senior Engineer Execution)
Purpose
Applies a pragmatic, senior-developer mindset to code changes: produces the smallest complete change that fully satisfies the task, eliminates premature abstractions and speculative bloat, enforces standard-library-first implementations, and leaves clear traceability for shortcuts.
Inputs required
- Active task context, bug report, user story (
docs/user-stories/), or accepted ADR (docs/adrs/). - Active codebase, callers, callees, and test fixtures.
- Optional level parameter (
lite,full[default],ultra,off).
Preconditions / governance gates
- Governance Alignment: Must adhere to
.agents/AGENTS.mdand the active change tier in the Change Classification Triage Matrix. - Tier 1 Gate: Ponytail cannot bypass the requirement for an Accepted Architectural Decision Record
(
docs/adrs/) if the proposed work involves architectural changes, breaking API contracts, data schema changes, or security posture modifications. - Rule 00 Compliance: Follows
.agents/rules/00-no-self-approval.md—the agent cannot self-approve its own implementations.
Procedure (mandatory)
- Map blast radius before writing:
- Identify every place the change must reach: callers, tests, fixtures, config, and exports.
- Verify potential breakage: data destruction, data exposure, or callers that stop working.
- Apply the smallest complete solution hierarchy:
- Verify if the code needs to exist: skip unrequested features, options, and flexibility.
- Reuse existing codebase helpers, components, services, and patterns.
- Standard library or platform features first: exhaust built-ins before reaching for external dependencies.
- Installed dependencies: use what is already present rather than introducing new packages.
- Strive for clarity: prefer concise, readable logic; keep values in native platform formats.
- Preserve structure: keep the repository's layers, interfaces, and conventions; deletion beats addition.
- Execute root-cause bug fixes:
- Inspect every caller of the touched function and fix the root cause once in shared code.
- Preserve error handling and input validation at trust boundaries.
- Annotate deliberate trade-offs and limits:
- When choosing an intentional simplification or shortcut with a known ceiling, annotate it explicitly (per
.agents/protocols/maintainability.md→ Technical debt governance):# shortcut: <the limit>, <upgrade trigger> (risk: <low|med|high>, track: <US-…|PRB-…>) - The
track:item must exist (user story indocs/user-stories/or problem record indocs/problem-records/); if it does not, draft it. A shortcut without atrack:reference is undocumented debt and is not allowed.
- When choosing an intentional simplification or shortcut with a known ceiling, annotate it explicitly (per
- Add proportional validation:
- For new non-trivial logic (branching, loops, parsers, security, financial calculations), write one focused test or assertion verifying behavior. Trivial changes require no extra test scaffolding.
- Apply level modifier:
- lite: Build what was requested; name the smaller option in one line and let the human decide.
- full (Default): Enforce rules 1–5; deliver the minimal diff.
- ultra: Actively challenge the premise before writing code; push back against parts unsupported by actual need.
- Format human handoff:
- End reply with 1–2 lines stating what was skipped/untested and any known risks.
- Include the standard governance
### Sourcesblock.
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.
- 8d ago First seen · 93 lines · 91 tokens per session scan A 40f536294a96
ponytail is a skill published in the GitHub repository dradoaica/cogov-a-sdlc (3 stars, last pushed 5d ago), licensed MIT. It adds 91 tokens to every session and 1,123 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-18.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.