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 alexmond/alexmskills --skill systemic-fixgit clone --depth 1 https://github.com/alexmond/alexmskillsWrote 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/alexmond/alexmskills/systemic-fix)<a href="https://agentmods.dev/skills/alexmond/alexmskills/systemic-fix"><img src="https://agentmods.dev/badge/skills/alexmond/alexmskills/systemic-fix/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/alexmond/alexmskills/systemic-fix"><img src="https://agentmods.dev/badge/skills/alexmond/alexmskills/systemic-fix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
SkillSpector: 1 finding, up to low
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- low Excessive Agency · line 22 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00134 | $0.02338 |
| Opus 5 | $0.00067 | $0.01169 |
| Sonnet 5 | $0.00027 | $0.00468 |
| Haiku 4.5 | $0.00013 | $0.00234 |
Grade A, and why
systemic-fix 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 6d 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
systemic-fix
When a bug is found, the default behaviour is to patch the line and stop. That misses two things: the same anti-pattern usually exists in sibling files or sibling modules (ticking regressions), and the bug is an instance of a class — a helper, a type, a lint rule, or a test can make the class unreproducible, but only if someone names the class first.
The discipline is to report before patching and default to the small fix. Without that default, the rule degenerates into refactor sprawl on every typo; without the report, scope expands silently and the user finds out from the diff. Never silently expand scope.
Gate — which bugs get the full loop
Correctness bugs only, by default: wrong behaviour, crashes, races, leaks, unhandled errors, regressions. Skip style nits, doc typos, and anything a CI-enforced linter already auto-fixes (those findings never reach a human, so they don't qualify as a class worth structural work). The profile refines this gate with the labels the repo's tracker actually uses (see below); when in doubt, run the scope check quietly and only surface a report if it finds something.
First run — calibrate (read-only)
If .claude/systemic-fix/profile.md does not exist in the current repo, calibrate before
the first report. Tell the user: "I'll scan the repo to learn its module map and bug
classes. ~30s, read-only." The scan captures:
- Module map — top-level source roots / submodules. The unit of "grep here first".
- Bug-class taxonomy — labels already in use on the issue tracker (
bug,regression,parsing, …); the test framework (so prevention-via-test is concrete); which lint rules CI already enforces (their findings are auto-caught and don't qualify). - Discipline-hook inventory — pre-commit checks, custom lint rulesets, architectural fitness functions (ArchUnit-style tests). These are the prevention options the repo already has; a prevention proposal should extend one of them before inventing a new tool.
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.
- 6d ago First seen · 197 lines · 134 tokens per session scan A ad45d64b5bb4
systemic-fix is a skill published in the GitHub repository alexmond/alexmskills (6 stars, last pushed 3d ago), licensed MIT. It adds 134 tokens to every session and 2,338 once invoked, about $0.0007 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 2026-09-05.
Other skills, from other repositories
manage-skills
A maintenance workflow for checking whether project verification skills still cover the code and rules that changed during a session.
systematic-debugging
Structured debugging methodology — use before proposing fixes for any error or failure. Covers: code bugs, build errors, deploy failures, config conflicts, dependency issues, infra problems. Also use when previous fix attempts failed or root cause is unclear.
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…
debugging-strategies
Master systematic debugging techniques, profiling tools, and root cause analysis to efficiently track down bugs across any codebase or technology stack. Use when investigating bugs, performance issues, or unexpected behavior.
extract-errors
Use when adding new error messages to React, or seeing "unknown error code" warnings.
error-audit
Audit code for silent error swallowing, fallbacks to degraded alternatives, backwards compatibility shims, and UI that fails to show errors to the user. Finds and fixes all occurrences in the specified scope.