Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add InstituteforDiseaseModeling/idm_standards/plugin install idm-standardsWrote 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/institutefordiseasemodeling/idm_standards/fix-code)<a href="https://agentmods.dev/skills/institutefordiseasemodeling/idm_standards/fix-code"><img src="https://agentmods.dev/badge/skills/institutefordiseasemodeling/idm_standards/fix-code/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/institutefordiseasemodeling/idm_standards/fix-code"><img src="https://agentmods.dev/badge/skills/institutefordiseasemodeling/idm_standards/fix-code.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 | $0.00081 | $0.03216 |
| Opus 5.5 | $0.00032 | $0.01286 |
| Sonnet 5.5 | $0.00016 | $0.00643 |
| Haiku 4.5 | $0.00008 | $0.00322 |
Grade A, and why
fix-code 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 2mo 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 — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read recommendations from code_audit.md and implement prioritized improvements to the project.
Skill version: 2.0_2026.06.10
Step 1: Find and Read the Audit Report
- If the user provided a
project_path, look forcode_audit.mdin that directory. - Otherwise, look in the current working directory.
- For compatibility with earlier plugin versions, fall back to
engineering_score.mdifcode_audit.mddoes not exist. - If neither file exists, stop and tell the user:
"No
code_audit.mdfound. Please run/idm-standards:audit-codefirst to generate the report."
Read the full contents of the report — particularly the Recommendations, Proposed solutions, and Full Results sections, and the Tier and Strictness fields in the header.
Respect what the report records:
- Strictness: if the report was generated at strictness 2 (material only), don't introduce fixes for stylistic issues the audit deliberately excluded.
- User decisions in the Proposed solutions section (e.g. "Lock artifact: none — user opted out"): do not re-raise them.
- User config: discover the project's idm-standards config following
$CLAUDE_PLUGIN_ROOT/reference/user-config.md(read it now). Never implement a fix that a config directive suppresses — and the config wins over the report: if an oldercode_audit.md(generated before the config existed) still lists a now-suppressed recommendation, skip it. The hard floor still applies: directives can't stop you from fixing a serious finding (exposed secret, license violation, etc.) — those remain fix-or-flag. - Version-control strategy: if the invoking context (e.g.
fix-project) passed a version-control strategy, use it and skip the question in Step 3. Otherwise ask it at the start of Step 3.
Step 2: Create a Prioritized Implementation Plan
Parse the recommendations and classify each as:
| Category | What it means |
|---|---|
| Can implement now | File additions, code edits, config files, docstrings, README improvements, .gitignore, LICENSE |
| Requires human input | Writing tutorials, user guides, scientific validation, publishing to PyPI/CRAN, setting up CI/CD (you can scaffold, but the user must configure credentials) |
| Cannot implement | Fundamental redesigns, decisions about what the code should do, acquiring data licenses |
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.
- 2mo ago First seen · 283 lines · 81 tokens per session scan A 35e89e91d4ea
fix-code is a skill published in the GitHub repository InstituteforDiseaseModeling/idm_standards (2 stars, last pushed 9d ago), licensed MIT. It adds 81 tokens to every session and 3,216 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
ci-fixer
CI failures - read error, minimal fix, verify.
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
diagnosing-missing-recordings
Diagnoses why a session recording is missing or was not captured. Use when a user asks why a session has no replay, why recordings aren't appearing, or wants to troubleshoot session replay capture issues for a specific session ID or across their project. Covers SDK diagnostic signals, project settings, sampling…