Borrowing it
Nothing to install: this file belongs to artvepa80/Agents-Hefesto. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/artvepa80/Agents-Hefesto/main/.claude/skills/hefestoai-language-learnings/SKILL.mdgit clone --depth 1 https://github.com/artvepa80/Agents-HefestoWrote 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/artvepa80/agents-hefesto/hefestoai-language-learnings)<a href="https://agentmods.dev/skills/artvepa80/agents-hefesto/hefestoai-language-learnings"><img src="https://agentmods.dev/badge/skills/artvepa80/agents-hefesto/hefestoai-language-learnings/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/artvepa80/agents-hefesto/hefestoai-language-learnings"><img src="https://agentmods.dev/badge/skills/artvepa80/agents-hefesto/hefestoai-language-learnings.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 | $0.00075 | $0.01321 |
| Opus 5.5 | $0.00030 | $0.00528 |
| Sonnet 5.5 | $0.00015 | $0.00264 |
| Haiku 4.5 | $0.00007 | $0.00132 |
Grade A, and why
hefestoai-language-learnings 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 yesterday.
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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HefestoAI language learnings
Short, verified notes on things that went wrong (or nearly did) in HefestoAI, with the fix and an
official source. This is an engineering skill for contributors and agents. It is not the
customer-facing product skill in skills/hefestoai/; leave that one alone.
When to use
- You are changing an analyzer, a rule, file discovery or language routing.
- A
hefesto analyzeresult looks wrong: a false positive, a missed rule, or "0 files analyzed". - A CI job, workflow, release step or local pre-push check is red.
Index
Read only the file you need.
| File | Covers |
|---|---|
| references/python.md | Python rules (HARDCODED_SECRET, ATTRIBUTE_NAME_MISMATCH, R3), mypy |
| references/js-ts.md | JavaScript/TypeScript: EVAL_USAGE, vendored files, tree-sitter tests |
| references/json.md | JSON analyzer (J001/J002/J004/J005), "Found 0 file(s)" |
| references/cobol.md | COBOL rules, copybooks, precision measurement |
| references/yaml-iac.md | YAML, Terraform and other IaC findings |
| references/github-actions.md | Workflow actions, runners, release.yml |
| references/tooling-ci.md | Local checks (ruff, mypy, guard), zero-files gate, CI behavior |
Entry format
Every entry uses exactly these fields:
### <short title>
- **Symptom:** what you see (message, rule id, CI status).
- **Cause:** why it happens, as established in the source.
- **Fix:** what was done or what to do.
- **Official source:** URL of the upstream documentation (or "n/a, internal behavior").
- **PR/commit:** PR number and/or commit SHA, or the CHANGELOG version.
- **Verified:** version or date it was last checked.
- **Status:** Fixed | Workaround | Open | Known limitation.
Adding an entry
- Only add something that happened in these repos and is written down: a CHANGELOG entry, a PR or a commit. Do not add guesses or general advice. Internal work logs are kept outside this repository and are not valid sources for the public copy.
- Open the source file or commit and check the claim before writing it. Cite it in PR/commit.
- Link the upstream documentation you used in Official source. If the behavior is our own code, say so.
- Put the entry in the file for its language or area. Keep it under about 10 lines.
- Add a line under
[Unreleased]inCHANGELOG.md, runagentskills validateon the skill folder (pip install skills-ref), and dogfood any changed code withHEFESTO_TELEMETRY=0 hefesto analyze(Markdown is not a supported format, so the skill files themselves report 0 files). - Public repo: run
python scripts/guard_public_repo.py. Internal topics (the paid package, billing, landing, hosted engine), private file paths, private PR numbers and agent handoffs never go in the public copy, and neither do internal agent names. The guard scans Markdown, code and config files for these; still read the whole diff by hand.
What ships with it
7 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.
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.
- yesterday Changed d07b6a0f6b62
- 2d ago Changed · +2 lines 0d8031b02035
- 9d ago First seen · 101 lines · 75 tokens per session scan A 6f2e972c20b6
hefestoai-language-learnings is a skill published in the GitHub repository artvepa80/Agents-Hefesto (7 stars, last pushed today), licensed MIT. It adds 75 tokens to every session and 1,321 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 2026-10-17.
Other skills, from other repositories
ci-triage
Classify CI failures — distinguish clear regressions from infra flakes and security-test failures. Produces structured failure reports.
atmos-lint
Atmos Terraform linting with TFLint: standalone atmos terraform lint, component-aware config discovery and toolchain versions, TFLint rule configuration, and lifecycle hooks/CI findings. Use when configuring, running, debugging, or documenting Terraform/OpenTofu linting in an Atmos project.
roam
Codebase comprehension via roam-code CLI. Use when exploring codebases, planning modifications, debugging failures, assessing PR risk, or checking architecture health. Triggers on: understanding project structure, pre-change safety checks, finding symbols/files, blast radius analysis, affected tests, health scoring…
github-actions
Use when authoring or fixing GitHub Actions CI/CD — workflows under .github/workflows, triggers, job matrix, caching, token permissions, OIDC cloud deploys, environment gates, reusable workflows. NOT the Dockerfile or image build strategy (that is docker), NOT the branching model (that is git-workflow), NOT release…
GitHub CI Fix Debugging
Debug and fix failing GitHub PR checks by inspecting GitHub Actions logs, summarizing failure context, drafting fix plans, and implementing fixes after approval.
ci-fix-monitor
Codex adapter for monitoring and fixing CI failures on opencode-swarm PRs. Use when diagnosing failed checks, fixing package-check (npm tarball) failures, resolving quality/lint/format errors, fixing macOS cross-platform file I/O failures, or watching a PR until all checks are green.