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 jamditis/claude-skills-journalism --skill ponytail-devgit clone --depth 1 https://github.com/jamditis/claude-skills-journalismWrote 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/jamditis/claude-skills-journalism/ponytail-dev)<a href="https://agentmods.dev/skills/jamditis/claude-skills-journalism/ponytail-dev"><img src="https://agentmods.dev/badge/skills/jamditis/claude-skills-journalism/ponytail-dev/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/jamditis/claude-skills-journalism/ponytail-dev"><img src="https://agentmods.dev/badge/skills/jamditis/claude-skills-journalism/ponytail-dev.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 | $0.00018 | $0.00425 |
| Opus 5.5 | $0.00007 | $0.00170 |
| Sonnet 5.5 | $0.00004 | $0.00085 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
ponytail-dev 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 today.
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.
What it actually says
Ponytail dev
Use this skill for software implementation, fixes, refactoring, infrastructure, tests, and technical review. In mixed work, treat the approved design as fixed input and apply this skill only to implementation.
Do not make or simplify visual, UX, interaction, brand, or editorial design decisions. Do not reduce design quality to save code.
Understand the affected flow before choosing a change. Prefer an existing pattern, the standard library, native platform features, or an installed dependency. Add only the code that the current requirement needs. Avoid speculative abstractions, compatibility layers, configuration, and extension points.
For a bug, find the root cause and inspect relevant callers. Fix a shared cause when the evidence supports that scope.
Verification
Use the smallest evidence that proves the result. Prefer an existing relevant test, focused command, build, type check, linter, temporary probe, or direct behavior check. Run broader checks when the changed scope, risk, repository rules, or CI behavior requires them.
Add a persistent test when it protects a likely repeat failure, stable public contract, non-obvious logic, or high-impact behavior. Static and trivial edits usually need direct inspection only.
Boundaries
Do not simplify away security controls, trust-boundary validation, data-loss protection, required error handling, accessibility, or an explicit requirement. Match the proof to the impact, uncertainty, and recovery cost.
Keep the handoff short. State the change, the evidence, and any known limit that affects the user's decision.
Related skills: vibe-coding (dev-toolkit) covers broader AI-assisted
development, and verification-before-completion (superjawn) covers final
proof before a completion claim.
Credit: Adapted from DietrichGebert/ponytail under the MIT license.
What ships with it
2 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.
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.
- today First seen · 51 lines · 18 tokens per session scan A cb9e1a662c72
ponytail-dev is a skill published in the GitHub repository jamditis/claude-skills-journalism (432 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 425 once invoked, about $0.0001 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 2026-10-25.
Other skills, from other repositories
symbolic-execution-assistant
Performs symbolic execution to detect potential errors by exploring execution paths, solving path constraints, and generating test inputs. Use when you need to analyze code for bugs like null dereferences, division by zero, buffer overflows, or assertion violations. Also use to generate test inputs that exercise…
code-repair-generation-combo
Automatically repair buggy code and generate comprehensive tests for Python, Java, and C++ programs. Use when users need to fix logic errors or runtime errors in functions, modules, or repositories. Accepts specifications via natural language descriptions, existing test cases, or input/output examples. Generates…
absolute-deflake
Flaky test fixes: detect nondeterministic tests empirically (repeat/shuffle/parallel runs), diagnose the root cause, fix it — never retry/skip/sleep — and verify across many randomized runs. Triggers on "absolute deflake", "fix flaky tests", "CI is flaky", "this test fails randomly/intermittently".
debug
Investigate a bug to its root cause systematically — reproduce, trace the data flow, test one hypothesis at a time — then fix it with a regression test. Use when something is broken and the user has a symptom or error message to chase down.
testing
A guide to software testing, including unit tests for small pieces of code, integration tests for connected parts, and functional tests for complete behaviours. It also explains TDD, a method where tests are written before the code.
test-execution
Orchestrate test execution — run unit, integration, and E2E tests, collect coverage reports, and analyze failures. Use when running tests, checking coverage, debugging test failures, or validating code changes before merge.