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 joao-aires/agent-skills-public --skill deliver-reliable-changesgit clone --depth 1 https://github.com/joao-aires/agent-skills-publicWrote 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/joao-aires/agent-skills-public/deliver-reliable-changes)<a href="https://agentmods.dev/skills/joao-aires/agent-skills-public/deliver-reliable-changes"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/deliver-reliable-changes/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/joao-aires/agent-skills-public/deliver-reliable-changes"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/deliver-reliable-changes.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 | $0.00043 | $0.01355 |
| Opus 5.5 | $0.00017 | $0.00542 |
| Sonnet 5.5 | $0.00009 | $0.00271 |
| Haiku 4.5 | $0.00004 | $0.00136 |
Grade A, and why
deliver-reliable-changes 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 yesterday.
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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read workflow framing for scope and invocation boundaries.
Deliver changes with evidence
Connect the requested outcome to observable acceptance, implement useful increments and verify the affected capability at its real boundary. Choose depth from changed risk and existing project requirements.
Establish the claim before implementation
Read accepted decisions, instructions and affected contracts. Preserve the existing architecture and UI direction unless changing them is the objective. Reuse agreed answers and the project's plan; a conversation can be sufficient scope. Use Git contributions for the objective worktree and contribution flow.
For a defect, reproduce the relevant failure before repairing it. Use diagnosing-bugs, tdd or specialist review where their method fits.
- Identify the state, authority, consumer and operating boundaries affected by the change.
- For substantial UI work, establish interaction direction and surface coverage with interaction design expertise; for backend work establish shared behavior before propagating it across entry points.
Describe what will be different when the work succeeds. Specify the starting condition, the action and the result the user or another consumer can observe. Include stored changes and denied actions where they matter, so the check can detect an implementation that appears successful while leaving the application in the wrong state.
Use those scenarios to guide implementation and verification. Keep material criteria stable; change them only when the underlying requirement has changed for a reason. Investigate a mismatch before adjusting the expected result. Record consequential assumptions and unavailable capabilities so a later report cannot turn an unexecuted check into a success claim.
Match evidence to the claim
| Claim | Sufficient kind of evidence |
|---|---|
| Implemented | Relevant code/configuration exists; missing behavior is identified. |
| Behavior verified | Affected acceptance, failure and authority cases ran at the stated persistence/provider/platform boundary. |
| Ready for deployment | Required checks pass and applicable configuration, compatibility, migration and recovery consequences are resolved. |
| Verified after deployment | The intended revision is served and the affected journey works in the named target. |
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.
- yesterday Changed · +24 lines 005b1494c22c
- 2d ago Changed a0ccfe9ea9a4
- 3d ago Changed · -33 lines 5130d4ee1c7b
- 5d ago Changed · +10 lines 8bf39e34bc42
- 7d ago Changed · +46 lines a79bc54a83c3
- 10d ago Changed · +5 lines 830205c6bebe
- 11d ago First seen · 42 lines · 43 tokens per session scan A 27c0a192f737
deliver-reliable-changes is a skill published in the GitHub repository joao-aires/agent-skills-public (2 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 1,355 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 2026-10-11.
Other skills, from other repositories
adk-go-self-review
Review an ADK Go change the way a maintainer will — a fresh-context pass over the whole diff, five lenses (correctness and tests, scope, simplicity, style, adk-python parity), and the mutation check that proves your tests pin the change. Use before opening a PR, before any later push that changes code, and when asked…
adversarial-reviewer
Stress-test a code change for concrete correctness defects, unsafe assumptions, and failure modes. Use when the user explicitly asks for an adversarial review, a deep bug hunt, or to tear a change apart, or to check your own change before submitting it. Do not use for ordinary review, style feedback, or general…
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
semgrep-rule-variant-creator
Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
plugin-review
Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.