Borrowing it
Nothing to install: this file belongs to juliakrivchikova/AccordAgents-desktop-app. 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/juliakrivchikova/AccordAgents-desktop-app/main/.agents/skills/implement-change/SKILL.mdgit clone --depth 1 https://github.com/juliakrivchikova/AccordAgents-desktop-appWrote 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/juliakrivchikova/accordagents-desktop-app/implement-change)<a href="https://agentmods.dev/skills/juliakrivchikova/accordagents-desktop-app/implement-change"><img src="https://agentmods.dev/badge/skills/juliakrivchikova/accordagents-desktop-app/implement-change/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/juliakrivchikova/accordagents-desktop-app/implement-change"><img src="https://agentmods.dev/badge/skills/juliakrivchikova/accordagents-desktop-app/implement-change.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 | $0.00171 | $0.01146 |
| Opus 5.5 | $0.00068 | $0.00458 |
| Sonnet 5.5 | $0.00034 | $0.00229 |
| Haiku 4.5 | $0.00017 | $0.00115 |
Grade A, and why
implement-change 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement Change
Own the change end to end. Do not replace implementation with planning or delegate participant-owned stages unless the user explicitly asks for delegation.
No size exemption
Every change goes through the whole workflow, whatever it looks like from the inside. There is no threshold below which the review and the end-to-end QA are skipped, and "it is one line", "it is only CSS", "I can see it is right by reading it", and "the User is waiting" are not reasons — they are the exact reasoning that has shipped broken work here more than once. A CSS fix that was obviously correct on inspection reached the User clipped, because a percentage height needs the parent to resolve one and reading the rule does not tell you whether it does.
Two consequences worth stating plainly:
- Speed is not yours to trade. Doing the QA costs minutes. If that delay matters, say so and let the User choose; never make the trade silently by skipping the step.
- A follow-up correction is a change too. The second, third and fourth attempts at the same defect each get the same treatment as the first. That is where the skipping usually happens.
Verify the affected lifecycle
Before editing, trace the affected path from the user action to its final result. Keep a compact map in the working context: states and transitions, who owns each state, and where data is applied, persisted, acknowledged or sent outside the app. Read the connected callers and consumers, including unchanged code.
For each new state or mechanism, identify its interactions with existing transitions and verify the applicable cases: cancellation before and during work, failure before and after persistence, duplicate or delayed delivery, reconnect, and restart. Choose cases from the actual path; do not invent irrelevant work. Exercise the coordinating path across its real boundaries; focused fault-injection tests support real end-to-end QA, and a helper test alone does not prove the caller.
What ships with it
1 file 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.
- 1mo ago First seen · 86 lines · 171 tokens per session scan A b8c517f16445
implement-change is a skill published in the GitHub repository juliakrivchikova/AccordAgents-desktop-app (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 171 tokens to every session and 1,146 once invoked, about $0.0007 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 2026-09-21.
Other skills, from other repositories
test-conversion-reviewer
Reviewer for converting unit tests to browser tests for Project Bedrock. Invoke this when the user needs to review their work while removing complex Browser dependencies from tests.
ln-51-acceptance-test-builder
Builds, updates or retires scoped acceptance tests and verifies execution; does not repair product code.
playwright-e2e-review
Audit Playwright E2E tests in the gc.platform suite (tests/playwright) against the four hard rules — no mocks, Page Object Model, work-by-fixture, one folder per frontend feature module — plus strict-TypeScript quality. Use whenever the user wants to review, check, audit, or "make sure it follows the conventions" for…
test-case-coverage
Audits an already-automated test case (TC-XXX) — one end-to-end journey across several use cases — against its document and reports a coverage matrix: which Flow rows, Validation items, and postconditions have a test step and code behind them, which are still open, and which test steps have drifted away from the test…
triaging-visual-review-runs
Inspects PostHog Visual Review (VR) runs that gate PR merges with screenshot regression checks. Use when the user mentions "visual review", "VR", "snapshot diff", "screenshot test", "storybook regression", "playwright snapshot", "quarantine", asks why a PR is blocked or what changed visually, wants to triage the VR…
full-stack-e2e-review
Run a rigorous end-to-end product or feature review across architecture, data, APIs, permissions, billing, tests, and real browser UX. Use for requests such as review this branch end to end, test everything, ensure no bugs, perform a full visual pass, or validate a multi-user workflow before merge or deploy.