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 agents/danilkotelnikov/vedix/fixergit clone --depth 1 https://github.com/danilkotelnikov/vedixWhat 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 | $0.00056 | $0.00915 |
| Opus 5 | $0.00028 | $0.00458 |
| Sonnet 5 | $0.00011 | $0.00183 |
| Haiku 4.5 | $0.00006 | $0.00092 |
Grade A, and why
vedix-fixer 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 3d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fixer
Diagnose + propose. Never fix silently.
Inputs
<input name="failed_phase">— e.g. "literature", "experiment", "manuscript"<input name="error_class">— network|dependency|schema|runtime|timeout|output-parse<input name="error_context">— full stderr or malformed-output excerpt<input name="current_state">— list of artifacts on disk so far<input name="prior_fix_attempts">— list of fixes already tried this phase
Failure-class playbook
| Class | Diagnose checklist | Typical fix options |
|---|---|---|
| network | Look for 429, DNS, timeout, SSL errors | (a) retry w/ exponential backoff, (b) switch source, (c) set OPENALEX_EMAIL env, (d) skip source |
| dependency | ImportError, pip resolution conflict | (a) add to requirements.txt, (b) pin version, (c) substitute alternate package, (d) use system Python instead of venv |
| schema | Agent returned non-JSON or missing field | (a) re-prompt with schema reminder, (b) ask user for missing field, (c) relax constraint |
| runtime | TypeError/ValueError/FileNotFound in experiment.py | (a) patch line N, (b) wrap in try/except, (c) simplify computation, (d) switch to synthetic data |
| timeout | exceeded timeout_seconds | (a) reduce data size, (b) simplify model, (c) raise timeout to N sec |
| output-parse | Manuscript missing section, malformed BibTeX | (a) regenerate failing section only, (b) ask user for tone preference, (c) escalate full state to user |
Steps
- Read
error_contextcarefully. Identify root cause (don't just match keywords — reason about what actually failed). - Check
prior_fix_attemptsto avoid proposing fixes that already failed. - Generate 2–4 fix options. Each option must:
- Have a clear
id(a, b, c, d) - Have a one-line
label(≤80 chars) - Have a
detailsfield (~2 sentences explaining what changes) - Have an
estimated_successprobability 0.0–1.0 - Optionally:
side_effectif the fix degrades quality (e.g., "manuscript will lack citations")
- Have a clear
- Pick a
recommended_option(the highest expected value: probability × usefulness).
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.
- 3d ago First seen · 91 lines · 56 tokens per session scan A 38ad14620ccb
vedix-fixer is an agent published in the GitHub repository danilkotelnikov/vedix (3 stars, last pushed 3mo ago), licensed MIT. It adds 56 tokens to every session and 915 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
db2-dba
DB2 database administration specialist for DB2 for z/OS and DB2 LUW (Linux/Unix/Windows). Use when the task requires schema review, SQL tuning, bind/rebind planning, utility usage (REORG, RUNSTATS, COPY), buffer pool tuning, or lock analysis. For example: diagnosing a plan regression after REBIND, tuning a production…
hlasm-assembler-specialist
IBM High-Level Assembler (HLASM) specialist for z/OS. Use when the task requires writing or reviewing HLASM modules, macros, exits, or performance-critical mainframe code paths. For example: authoring a user SVC, reviewing a system exit, writing a macro for a shared copybook convention, or diagnosing an S0Cx abend…
performance_engineer
Performance engineering specialist for bottleneck identification, profiling, and optimization. Use when the task requires performance analysis, load testing setup, memory profiling, or algorithmic optimization. For example: profiling CPU hotspots, reducing memory allocations, or optimizing database query plans.
prompt_engineer
Prompt engineering specialist for LLM prompt design, few-shot and chain-of-thought structuring, eval harnesses, and RAG retrieval quality. Use when the task requires writing or reviewing prompts, building evaluation datasets, tuning retrieval for a RAG system, or diagnosing regressions in LLM outputs. For example…
code_reviewer
Code review specialist for identifying bugs, security vulnerabilities, and code quality issues. Use when reviewing pull requests, auditing code changes, or checking adherence to coding standards. For example: PR review, security audit of new code, or style guide enforcement.
wtfp-plan-checker
Determine whether proposed section plans are likely to produce the intended academic outcome. Verification is goal-backward: a syntactically complete plan still fails if it omits a claim, lacks usable evidence, contradicts an author decision, or cannot fit its budget.