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 navapbc/digital-service-orchestra --skill oscillation-checkgit clone --depth 1 https://github.com/navapbc/digital-service-orchestraWrote 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/navapbc/digital-service-orchestra/oscillation-check)<a href="https://agentmods.dev/skills/navapbc/digital-service-orchestra/oscillation-check"><img src="https://agentmods.dev/badge/skills/navapbc/digital-service-orchestra/oscillation-check/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/navapbc/digital-service-orchestra/oscillation-check"><img src="https://agentmods.dev/badge/skills/navapbc/digital-service-orchestra/oscillation-check.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 | $0.00152 | $0.01071 |
| Opus 5 | $0.00076 | $0.00535 |
| Sonnet 5 | $0.00030 | $0.00214 |
| Haiku 4.5 | $0.00015 | $0.00107 |
Grade A, and why
oscillation-check 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Oscillation Check
Detects when iterative review feedback would revert changes made by a previous iteration -- preventing infinite fix-revert-fix loops.
When to Use
Invoke as a sub-agent from:
- CLAUDE.md review loop: Before implementing
/dso:reviewfeedback on iteration 2+ /dso:sprintPhase I: Before creating remediation tasks from re-validation/dso:debug-everythingPhase H Step 5: Before retrying a fix after critic CONCERN
Input
The orchestrator provides:
files_targeted: List of files the current feedback wants to modifyiteration: Current iteration number (1-indexed)context: One ofreview,remediation,criticcommit_before_previous_fix: Git commit SHA from before the previous iteration's changes (optional -- if not provided, useHEAD~1)epic_id: (forremediationcontext only) The epic whose children to check
Protocol
For review and critic context:
- Check if this is iteration 1 -> output
CLEAR(no previous iteration to compare) - For iteration 2+:
a. Get the diff of what the previous iteration changed:
b. If the diff is empty (previous iteration didn't touch these files) ->git diff {commit_before_previous_fix}..HEAD -- {files_targeted}CLEARc. If the diff is non-empty: the current feedback targets files that were already modified. Analyze the feedback direction:- Read the current feedback items for these files
- Compare against the previous iteration's changes shown in the diff
- If the feedback would undo previous changes (revert direction) ->
OSCILLATION - If the feedback would build on previous changes (same direction) ->
CLEAR
For remediation context:
- Get closed remediation tasks from the epic:
Filter for tasks with "Fix:" prefix and status=closed..claude/scripts/dso ticket deps {epic_id} - For each closed remediation task, read its notes (
.claude/scripts/dso ticket show <id>) to find modified files. - Compare
files_targetedagainst the closed tasks' modified files. - If overlap exists ->
OSCILLATION(same files being re-remediated) - If no overlap ->
CLEAR
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 · 94 lines · 152 tokens per session scan A 90b2fe97343e
oscillation-check is a skill published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed today), licensed Apache-2.0. It adds 152 tokens to every session and 1,071 once invoked, about $0.0008 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 2026-09-03.
Other skills, from other repositories
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
gsd-ns-review
Route to the appropriate quality / review skill based on the user's intent. gsd-code-review-fix was absorbed by gsd-code-review --fix in #2790.
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
gitnexus
A code-graph analysis add-on for examining an existing codebase, including symbols, call paths, execution flows, and effects across repositories. It can query GitNexus through its command-line or MCP interfaces.
cleanup-code-inspections
Reduce technical debt and improve code quality by systematically resolving static analysis warnings.
sonarqube-mcp
Provides SonarQube and SonarCloud integration patterns via the Model Context Protocol (MCP) server. Enables quality gate monitoring, issue discovery and triaging, pre-push code analysis, and rule education directly in the agent workflow. Use when the user wants to check quality gates, search for Sonar issues, analyze…