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 vshvedov/elephant-goldfish --skill eg-fix-buggit clone --depth 1 https://github.com/vshvedov/elephant-goldfishWrote 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/vshvedov/elephant-goldfish/eg-fix-bug)<a href="https://agentmods.dev/skills/vshvedov/elephant-goldfish/eg-fix-bug"><img src="https://agentmods.dev/badge/skills/vshvedov/elephant-goldfish/eg-fix-bug/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/vshvedov/elephant-goldfish/eg-fix-bug"><img src="https://agentmods.dev/badge/skills/vshvedov/elephant-goldfish/eg-fix-bug.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 | $0.00029 | $0.00963 |
| Opus 5.5 | $0.00012 | $0.00385 |
| Sonnet 5.5 | $0.00006 | $0.00193 |
| Haiku 4.5 | $0.00003 | $0.00096 |
Grade A, and why
eg-fix-bug scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
For UI bugs, use the project-appropriate manual verification path. Prefer Browser Use / the in-app browser for web apps, a simulator/device run for mobile apps, and curl/log/test reproduction for backend-only services. S How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EG Fix Bug Skill
Fix a bug using the elephant/goldfish workflow. Use the user's text around the $eg-fix-bug skill mention as the bug description. If no description is provided, ask for one.
If the bug description is a GitHub issue URL or #<number>, fetch it with gh issue view <number> --json title,body,labels,comments and seed the problem doc from it.
Triviality Gate
Skip the goldfish/test ceremony for typo fixes in copy/comments, dead-code removal, version bumps, formatter-only diffs, and single-line config tweaks. Still run eg-precommit-review and the test gate.
Run the full loop for everything else.
Problem Doc
Print:
PROBLEM DOC
- Symptom: <what the user observes>
- Repro: <steps, failing test, URL, log, screenshot, or "need to derive">
- Suspected area: <file/module/route/job/screen>
- Hypothesized root cause: <one sentence>
- Blast radius: <surfaces that could be affected>
- Fixed means: <specific test/behavior/output>
If there is no repro and the bug is not obvious from a single file read, stop and ask for a concrete repro path.
For UI bugs, use the project-appropriate manual verification path. Prefer Browser Use / the in-app browser for web apps, a simulator/device run for mobile apps, and curl/log/test reproduction for backend-only services. Start or identify the dev server from package scripts, AGENTS.md/CLAUDE.md, or CI docs when needed.
Goldfish Diagnosis
The user invoked this skill, so a fresh diagnosis subagent is explicitly authorized.
Spawn a fresh Codex subagent with fork_context: false. Use agent_type: "explorer" for narrow codebase lookup when available; otherwise use default.
Send only the symptom and repro, not the elephant's hypothesized root cause:
Independent diagnosis of a bug in this repo. AGENTS.md and CLAUDE.md may contain architecture notes.
Symptom: <FILL IN>
Repro: <FILL IN>
Investigate. Where is the bug most likely to live? Cite file:line locations. List the top 1-3 candidate root causes ranked by likelihood. For each, name supporting evidence and what would falsify it. Do not propose a fix yet.
If UI repro is needed, use the project-appropriate browser/simulator path only if available and safe.
End with `diagnosis complete`.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 104 lines · 29 tokens per session scan A 37b2d3e397aa
eg-fix-bug is a skill published in the GitHub repository vshvedov/elephant-goldfish (74 stars, last pushed 5mo ago), licensed MIT. It adds 29 tokens to every session and 963 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
evidence-audit
Evidence-led audit/fix rounds for any codebase in any language. Finds only defects that a runnable proof reproduces on current code, applies the narrowest in-scope patch, verifies with a second proof, promotes high-risk proofs to permanent regression tests, and reports exact validation results. Use whenever the user…
bug-hunter
Use this skill when scanning source code for bugs, anti-patterns, code smells, or quality issues in a codebase, or when running a proof-driven bug hunt that must find, prove, fix, and verify one real defect. Trigger on the explicit vocabulary — "bug", "bug hunt", "/bughunt", "scan for issues", "find problems"…
debugging
Use this skill when something is broken and the cause is unknown — a failing test, a crash, an error message, wrong output, a regression, a hang, or behaviour that differs between environments — and it has to be found and fixed at the root. Also use it to build the failing proof for a suspected defect before fixing…
observability
Use this skill when adding or reviewing logging, metrics, or tracing in an application, or when a production problem can't be diagnosed from the signals that exist today. Triggers: user says "logging", "logs", "trace", "tracing", "metrics", "observability", "instrument", "OpenTelemetry", "structured logging", "log…
incident-response
Diagnose and recover an owned service incident with bounded changes, timeline evidence and verified health. Use during outages, bad deployments or data/service degradation; preserve evidence and separate mitigation from root-cause repair.
remote-debugging
Diagnose a reported application failure on explicitly authorized remote hosts using bounded logs and runtime evidence. Use when local behavior differs from a known server or deployment; start read-only and keep diagnosis separate from disruptive remediation.