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 agentmods add skills/seqra/opentaint/debug-rulenpx skills add seqra/opentaint --skill debug-rulegit clone --depth 1 https://github.com/seqra/opentaintWhat 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 | $0.00040 | $0.01194 |
| Opus 5 | $0.00020 | $0.00597 |
| Sonnet 5 | $0.00008 | $0.00239 |
| Haiku 4.5 | $0.00004 | $0.00119 |
Grade A, and why
debug-rule 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Debug Rule
Diagnose why a rule or approximation behaves unexpectedly on a model by tracing where taint is dropped, and decide who owns the fix: the rule, a missing library model, or the engine.
Inputs
Provided by the caller, fall back to the default value when omitted. Ask back only when a required input is missing and has no sensible default
project-root(optional) — root of the target project. Opentaint keeps all analysis artifacts under the fixed<project-root>/.opentaint/directory, so every.opentaint/...path below resolves there. Default: current directoryrule(required) — the one rule whose sample or flow routes taint through the code under test, as<ruleSetRelativePath>.yaml:<shortId>. For an approximation, the rule whose sample routes taint through the approximated methodmodel(required) — the project model where the behavior shows up
Workflow
1. Reproduce and localize the kill
Reproduce the exact run that showed the problem — same model, rulesets, and applied approximation dirs — and trace where taint dies with a fact-reachability run. Run it directly as a foreground, blocking command and wait for exit — never background it or use Monitor:
opentaint test rule reachability <rule> \
--project-model <model> \
-o <results-dir>/report.sarif \
--ruleset builtin --ruleset .opentaint/rules \
--passthrough-approximations .opentaint/pass-through \
--dataflow-approximations .opentaint/dataflow
<results-dir> is .opentaint/test-results/<name> for a test model, .opentaint/results for the main scan. The per-instruction facts are in the sibling <results-dir>/debug-ifds-fact-reachability.sarif, not the -o file — the -o SARIF only shows whether the rule fired. Read that sibling to find the kill:
- a missed detection (a positive that won't pass, or a flow absent from a scan) — confirm a fact exists at the source; if none, the gap is in
pattern-sources, not the flow. Otherwise walk the facts to the last instruction still carrying it and the first where it's gone — that gap is the kill - a spurious detection (a negative that fires) — the reverse: find where a fact appears with no tainted input reaching it
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 First seen · 66 lines · 40 tokens per session scan A cf2ce90c8012
debug-rule is a skill published in the GitHub repository seqra/opentaint (149 stars, last pushed 2d ago), licensed Apache-2.0. It adds 40 tokens to every session and 1,194 once invoked, about $0.0002 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
plugin-code-review-orchestrated
Orchestrates a code review of the spring-plugin repository through scope/context passes, routing, domain reviewer subskills, and per-artifact validation. Use when asked to review a PR, diff, commit, branch, module, or file set, to run a full orchestrated review, or to produce a validated review report.
github-issue-manager
Classifies a user request as Bug, Compatibility, Feature, Question, or Task for the explyt/spring-plugin GitHub repo, lightly researches the relevant codebase, searches similar existing issues, and either reports an existing issue or creates a correctly titled and labeled one following the repository issue forms. Use…
review-async-lifecycle
Normative reviewer for EDT safety, coroutines, cancellation, read/write actions, disposal, listeners and async lifecycle in the explyt spring-plugin. Use during orchestrated code review when the diff touches threading, background tasks, read or write actions, listeners, MessageBus, Disposable ownership or progress…
review-core-correctness
Normative mandatory reviewer for correctness, contracts, architecture sanity, UX behavior, code quality and tests in the explyt spring-plugin codebase. Use during orchestrated code review of a PR, diff, commit or branch, or when asked to review correctness, logic, architecture or test coverage of plugin changes.
review-findings-validator
Normative per-artifact validator: reads exactly one reviewer artifact, re-verifies every claim against real source code, classifies findings as TP, FP, or Need more data, and writes exactly one validated artifact. Use during the validation wave of an orchestrated code review, when asked to validate reviewer findings…
review-persistence-security-resources
Normative reviewer for persistence, settings, secrets, logging hygiene, resources, caches, cross-platform behavior and long-lived state in the explyt/spring-plugin IntelliJ plugin. Use when reviewing changes that touch PersistentStateComponent, settings UI, credentials, caches, service fields, logging, file paths…