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 orin-dx/agent-plugins --skill implementgit clone --depth 1 https://github.com/orin-dx/agent-pluginsWrote 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/orin-dx/agent-plugins/implement)<a href="https://agentmods.dev/skills/orin-dx/agent-plugins/implement"><img src="https://agentmods.dev/badge/skills/orin-dx/agent-plugins/implement/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/orin-dx/agent-plugins/implement"><img src="https://agentmods.dev/badge/skills/orin-dx/agent-plugins/implement.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 | $0.00051 | $0.01129 |
| Opus 5.5 | $0.00020 | $0.00452 |
| Sonnet 5.5 | $0.00010 | $0.00226 |
| Haiku 4.5 | $0.00005 | $0.00113 |
Grade A, and why
implement 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 1mo 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
State material concerns, evidence, consequence, and confidence directly. Do not soften blockers, manufacture praise, or claim certainty beyond the evidence.
Implement with evidence
Outcome
Make the requested workspace change in bounded batches and return a scoped verdict grounded in current code, risk-based verification, and defect-family review.
Workflow
- Prefer a persisted
plan@1. Read it fromplan_file_pathand its source spec fromspec_file_path; validate them withshared/schemas/[email protected]andshared/schemas/[email protected]. - Verify the plan’s
spec_hashagainst the raw spec file bytes. Stop and report drift if it differs; a stale plan cannot silently govern implementation. - Produce
workspace-manifest@1from current repository state, every affected language, project-native verification capabilities, baseline tests, and exposed workflow provenance. - Execute one cohesive subsystem batch. Choose the smallest safe implementation and verification methods from the changed risks and
shared/references/verification/evidence.md. - Record
implementation-result@1with exact criterion locations, commands, observations, boundaries, and environment evidence. - Use available mutation tooling against changed behavior or a safe deliberate-fault check. Record
mutation-report@2; unavailable evidence is a coverage gap. - Produce
implementation-review@2. Judge verification fit, sibling completeness, semantic models, and architecture. - Before completion, account for every planned batch and started verification task, reread persisted artifacts and current code, independently challenge semantic completeness, and emit scoped
verdict@3. Commit only after user authorization.
Defect-family review
Before reviewing, load shared/references/verification/implementation-review.md and the evidence it selects. For each changed defect, assess:
- Syntactic siblings with the same code shape or algorithm.
- Semantic siblings with the same domain responsibility or failure state.
- Candidate sites supporting semantic completeness, including zero-match claims.
- The shared root cause for related instances.
- Missing concepts, states, operations, boundaries, abstractions, invariants, or enforcement.
- One disposition: fix instances, unify implementation, escalate architecture, or explicitly defer.
- Boundary reach, input-space method, relevant environments, external-state freshness, and coverage gaps.
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.
- 1mo ago Changed · +2 lines 6fc70e8a204c
- 1mo ago Changed · +23 lines 5c3266fa8bce
- 1mo ago Changed · -61 lines · -128 tokens per session 6a0475e4667f
- 1mo ago Changed · +3 lines · +13 tokens per session 1c01b9b8186c
- 2mo ago First seen · 104 lines · 166 tokens per session scan A af4f664ef616
implement is a skill published in the GitHub repository orin-dx/agent-plugins (1 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 1,129 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
test-driven-development
Drives development with tests using the red-green-refactor loop. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality. Use when asked to add tests to a function, fix a bug…
setup
Set up or update TDD Guard for the current project. Detects the test framework, installs or updates the matching reporter, and configures or migrates its configuration to match the current specification.
conductor-implement
Execute tasks from a track's implementation plan following TDD workflow.
tdd
AI DevKit · Test-driven development — write a failing test before writing production code. Use when implementing new functionality, adding behavior, or fixing bugs during active development.
software-code-refactoring
Improve production code quality while preserving all existing test behavior. Commonly used for the Refactor phase of TDD red-green-refactor, but applicable to any codebase with tests. Use when production code works but needs cleanup — reducing duplication, improving naming, simplifying complexity, aligning with…
testing-principles
Language-agnostic testing principles for choosing which tests a change needs, test quality, and proof ownership, with frontend and browser E2E implementation references. Use when writing tests, deciding test scope, or reviewing test quality.