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 eric-cielo/moflo --skill guidancegit clone --depth 1 https://github.com/eric-cielo/mofloWrote 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/eric-cielo/moflo/guidance)<a href="https://agentmods.dev/skills/eric-cielo/moflo/guidance"><img src="https://agentmods.dev/badge/skills/eric-cielo/moflo/guidance/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/eric-cielo/moflo/guidance"><img src="https://agentmods.dev/badge/skills/eric-cielo/moflo/guidance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
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 →
- high Prompt Injection · line 176 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Agent Snooping · line 275 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- medium Data Exfiltration · line 235 Code scans file system directories looking for sensitive files. This could be reconnaissance for credential theft.Fix: Remove unnecessary filesystem scanning. If file access is needed, use explicit, scoped paths. Avoid reading ~/.ssh, ~/.aws, or credential directories.
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 | $0.00070 | $0.05059 |
| Opus 5.5 | $0.00028 | $0.02024 |
| Sonnet 5.5 | $0.00014 | $0.01012 |
| Haiku 4.5 | $0.00007 | $0.00506 |
Grade A, and why
guidance 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 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.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
**Cross-reference:** for each detected concern, grep the existing `.claude/guidance/` corpus for keyword coverage. A topic is a **gap** if (a) the concern shows up in code (not just transitive deps) and (b) no existing g Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 338 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/guidance — Author and audit project guidance
Help the user write, edit, or audit guidance docs. By default the skill writes guidance for Claude into .claude/guidance/ as Markdown and enforces the universal rules from .claude/guidance/moflo-guidance-rules.md (the single source of truth — do not paraphrase or duplicate). Flags switch the audience (-h → humans) and the output format (--html → HTML).
Arguments: $ARGUMENTS
Modes and flags
| Flag | Effect |
|---|---|
| (none) | Single-doc mode for Claude — Markdown, full universal rules, destination .claude/guidance/<kebab-topic>.md |
-h |
Switch audience to humans — Markdown, lighter human ruleset, destination docs/<kebab-topic>.md |
--html |
Emit HTML (with the minimal default stylesheet from Step 2.5) instead of Markdown. Composes with -h. |
-a |
Audit mode — two-pass triage of .claude/guidance/ (Claude only). Cannot combine with -h or --html. |
<topic-or-path> |
Topic name (kebab-cased into the default destination) or an explicit file path that overrides the default destination. |
Combos:
-h --html→ HTML for humans, default destinationdocs/<kebab-topic>.html--htmlalone → HTML for Claude. Unusual: Claude reads Markdown, not HTML. Warn the user and offer to add-h(write todocs/instead).- An explicit
<path>always wins over the default destination. If the path's directory contradicts the audience flag (e.g.-h .claude/guidance/foo.md), warn but honor the path. -a -h/-a --html→ reject; audit mode targets.claude/guidance/(Claude) and emits a triage report, not a doc.
Step 0 — Memory First
Before reading any files, run a memory search:
mcp__moflo__memory_search { query: "guidance rules writing project conventions", namespace: "guidance" }
This pulls the user's project-specific guidance conventions (if any) plus the moflo universal rules into context. The memory-first gate will block file reads otherwise.
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 · 338 lines · 70 tokens per session scan A 00bc672bc135
guidance is a skill published in the GitHub repository eric-cielo/moflo (19 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session and 5,059 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
guidance compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| guidanceeric-cielo/moflo | Skill | 19 | yesterday | MIT | A | 70 | Claude Code |
| workspace-organizingnextlevelbuilder/goclaw | Skill | 3.7k | yesterday | none | A | 0 | Claude Code, Codex |
| five-whysshawnclybor/clybor-claude-tooling | Skill | 6 | 2d ago | MIT | A | 148 | Claude Code |
| why-diagnosticshawnclybor/clybor-claude-tooling | Skill | 6 | 2d ago | MIT | A | 100 | Claude Code |
| ralph-loopshawnclybor/clybor-claude-tooling | Skill | 6 | 2d ago | MIT | A | 110 | Claude Code |
| securityNexaDuo/mARC | Skill | 7 | 3d ago | MIT | A | 28 | Claude Code, Codex |
| sreNexaDuo/mARC | Skill | 7 | 3d ago | MIT | A | 34 | Claude Code |