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 bgauryy/octocode --skill octocode-researchgit clone --depth 1 https://github.com/bgauryy/octocodeWrote 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/bgauryy/octocode/octocode-research)<a href="https://agentmods.dev/skills/bgauryy/octocode/octocode-research"><img src="https://agentmods.dev/badge/skills/bgauryy/octocode/octocode-research/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/bgauryy/octocode/octocode-research"><img src="https://agentmods.dev/badge/skills/bgauryy/octocode/octocode-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
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 →
- medium MCP Rug Pull · line 54 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 57 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 58 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 59 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00148 | $0.01343 |
| Opus 5 | $0.00074 | $0.00672 |
| Sonnet 5 | $0.00030 | $0.00269 |
| Haiku 4.5 | $0.00015 | $0.00134 |
Grade A, and why
octocode-research 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 12d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Octocode Research
Evidence before assertion. Find the anchor, read the exact bytes, prove the claim, then answer or patch.
FRAME → CLASSIFY → MODEL → SEARCH → READ EXACT → PROVE → DECIDE/PATCH → VERIFY
That's the full shape, not a checklist to march through. Scale it to the claim: a small lookup gets a cheap read and an honest confidence label; a delete, a merge verdict, or a root cause earns the whole ladder. Skip stages you can already answer — but say which ones you skipped.
The rules
- Open with one line: corpus, actual vs desired, task class, mode, surfaces used and skipped.
- Call it a bug only when evidence shows a supported contract was violated.
- Root cause needs mechanism, trigger, violated contract, divergence boundary, and a killed alternate.
- Use the strongest handle you already hold. For nontrivial claims check two of: structure, stream, connections.
- A snippet is a lead. Empty means this lane can't see it, not it isn't there. Say which you mean.
- Track
claim → evidence → confidence → next check. Cite exact anchors, and only checks that actually ran. - Ask before broad contracts, deletes/renames, thin evidence, or a third unrelated search space. Patch after proof.
Stop when: grounded evidence answers the framed question and the alternate is dead; no cheap next step can change the conclusion; the budget is hit (default 3-5 decisive iterations or ~15 minutes); the last iterations changed no state; retries stay thin, or a license/product/architecture call belongs to the user; a gate blocks (broad contract, delete/rename, clone or run untrusted code, unapproved artifact write); or a skill edit measured flat/worse — revert through references/improve-loop.md. Report the remaining gaps instead of padding certainty.
Workflows
Start with references/algorithm.md (routing, evidence grades) and references/problem-framing.md (is this a bug, feature, enhancement, or still unknown?). Then pick one route by what you're looking at — load references/workflows.md when you need the per-route detail, the load budget per task size, or the handoff receipt between routes:
What ships with it
23 files 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.
- agents/openai.yaml 295 B
- README.md 3.5 KB
- references/algorithm.md 3.0 KB
- references/code-research.md 3.3 KB
- references/github-landscape.md 2.3 KB
- references/improve-loop.md 2.0 KB
- references/long-research.md 2.4 KB
- references/loop-mode.md 2.3 KB
- references/octocode.md 4.6 KB
- references/problem-framing.md 2.3 KB
- references/research-flow.md 3.1 KB
- references/researcher-mindset.md 4.4 KB
- references/workflow-change.md 1.8 KB
- references/workflow-combination.md 2.2 KB
- references/workflow-debug.md 1.9 KB
- references/workflow-external.md 1.8 KB
- references/workflow-local.md 1.3 KB
- references/workflow-pr-review-analysis.md 2.8 KB
- references/workflow-pr-review-report.md 2.1 KB
- references/workflow-pr-review.md 2.9 KB
- references/workflow-refactor.md 2.7 KB
- references/workflows.md 3.9 KB
- scripts/check-description.mjs 1.8 KB runs code
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.
- 12d ago First seen · 75 lines · 148 tokens per session scan A 0dd7a864064c
octocode-research is a skill published in the GitHub repository bgauryy/octocode (932 stars, last pushed today), licensed MIT. It adds 148 tokens to every session and 1,343 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 2026-08-30.
Other skills, from other repositories
fix-tests
Systematic workflow for diagnosing and fixing failing tests. Use when the user reports failing tests or asks to fix test failures.
query-optimization
Workflow for identifying and fixing slow database queries. Use when a query is slow or the user asks to optimize database performance.
debug-issue
Structured workflow for debugging a reported or reproduced issue. Use when the user asks to debug a bug, find root cause, or fix a failing scenario.
agenttrace-session-audit
Audit local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI gates.
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…
widget-design
Best practices for designing UI widgets in xmcp. Use when creating interactive widgets for GPT Apps or MCP Apps, choosing between React components and template literals, designing widget layouts, handling state and data fetching, or troubleshooting widget rendering issues.