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 synthesisengineering/synthesis-skills --skill synthesis-implementation-integritygit clone --depth 1 https://github.com/synthesisengineering/synthesis-skillsWrote 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/synthesisengineering/synthesis-skills/synthesis-implementation-integrity)<a href="https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-implementation-integrity"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-implementation-integrity.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00094 | $0.05788 |
| Opus 5 | $0.00047 | $0.02894 |
| Sonnet 5 | $0.00019 | $0.01158 |
| Haiku 4.5 | $0.00009 | $0.00579 |
Grade A, and why
synthesis-implementation-integrity 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 — 446 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synthesis Implementation Integrity
The most dangerous moment in software development is when you believe you're done. That belief shuts down scrutiny exactly when scrutiny matters most.
This skill is an adversarial self-review protocol. It challenges you — human or AI agent — to systematically prove your implementation is complete rather than assuming it is. The discipline: look for evidence that the work is WRONG, not confirmation that it's right. Confirmation bias is the default mode; this protocol overrides it.
"Tests pass" is not proof of correctness. Tests create their own world — fresh databases, mocked dependencies, controlled inputs. Production is a different world with persistent state, real external services, cached assets, and environment configurations that no test suite reproduces. The gap between "tests pass" and "production works" is where the worst failures live, because everyone has stopped looking.
This protocol exists to keep looking.
When to Invoke
Run this protocol:
- After completing any non-trivial implementation — before declaring it done
- After adding a field, column, or property that flows through multiple system layers
- After implementing the same pattern across multiple components — the last one gets the least attention
- After all tests pass on a schema, config, or deployment change — for these change types, "all tests pass" should trigger deeper scrutiny, not signal that verification is over
- When someone (human or AI) says "it's done" — use this to give an evidence-based answer
Skip for trivial changes (typo fixes, comment updates, single-line config edits).
Where This Fits — Verification Chain
Five complementary skills cover verification at different scopes and lifecycle phases:
| Skill | Scope | Cadence | Core question |
|---|---|---|---|
| synthesis-implementation-integrity (this one) | A single change | After every non-trivial implementation | "Is this change genuinely complete?" |
| synthesis-code-audit | A diff (changed code) | After implementation, before or during review | "Does this diff meet quality standards?" |
| synthesis-preflight | A branch | Before creating a PR | "Is this branch ready to merge?" |
| synthesis-pr-review | A change proposed for merge | Every pull request | "Should this change enter the codebase?" |
| synthesis-codebase-review | The entire system | Periodic or at milestones | "Is this system healthy?" |
What ships with it
5 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.
- 8d ago First seen · 446 lines · 94 tokens per session scan A 132236e4f4d7
synthesis-implementation-integrity is a skill published in the GitHub repository synthesisengineering/synthesis-skills (18 stars, last pushed yesterday), licensed Apache-2.0. It adds 94 tokens to every session and 5,788 once invoked, about $0.0005 per session on Opus 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 2026-08-30.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…