Borrowing it
Nothing to install: this file belongs to unbound-force/gaze. 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/unbound-force/gaze/main/.opencode/skills/always-on-guidance/SKILL.mdgit clone --depth 1 https://github.com/unbound-force/gazeWrote 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/unbound-force/gaze/always-on-guidance)<a href="https://agentmods.dev/skills/unbound-force/gaze/always-on-guidance"><img src="https://agentmods.dev/badge/skills/unbound-force/gaze/always-on-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/unbound-force/gaze/always-on-guidance"><img src="https://agentmods.dev/badge/skills/unbound-force/gaze/always-on-guidance.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 | $0.00012 | $0.00447 |
| Opus 5.5 | $0.00005 | $0.00179 |
| Sonnet 5.5 | $0.00002 | $0.00089 |
| Haiku 4.5 | $0.00001 | $0.00045 |
Grade A, and why
always-on-guidance 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 8d 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.
What it actually says
Always-On Guidance
Rules that apply to every coding session.
Tool Usage Discipline
- Read files before editing — never guess at content
- Use
replicator_org_*tools for work item management - Use
replicator_comms_*tools for agent messaging and file reservations - Use
replicator_forge_*tools for multi-agent coordination - Use
dewey_store_learning/dewey_semantic_searchfor learning storage and retrieval - Check
dewey_semantic_searchbefore solving problems from scratch
Code Quality
- Functions do one thing well
- Names reveal intent — no abbreviations
- Comments explain why, not what
- No dead code or unused imports
- Error messages include context
Testing
- Write tests for all new code
- Use
db.OpenMemory()for database tests - Use
t.TempDir()for filesystem tests - Standard library
testingpackage only — no testify - Test names:
TestXxx_Description
Error Handling
- Return errors, don't panic
- Wrap errors with context:
fmt.Errorf("operation: %w", err) - Handle all error paths — no ignored returns
- Use
errors.Isfor sentinel error checks
Command Template Fidelity
- When a command template prescribes a fixed exit or output format, re-read that section from the template file before emitting — especially after context compression
- After compression, the template file is the sole authority for prescribed output format — never reconstruct it from memory or compressed summaries
Tool Output Overflow Recovery
When any tool result reports overflow to a file
(matching the pattern "Full output saved to: "),
read only the missing sections with offset/limit;
never read the whole file.
Git Discipline
- Conventional commits:
type: description - Never force push to main
- Commit early, commit often
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.
- 8d ago Changed · +7 lines c3653330db0b
- 1mo ago Changed 7551500f6f50
- 2mo ago Changed · +11 lines 990655c57c24
- 2mo ago First seen · 48 lines · 12 tokens per session scan A a9e72a1be9b6
always-on-guidance is a skill published in the GitHub repository unbound-force/gaze (4 stars, last pushed yesterday), licensed Apache-2.0. It adds 12 tokens to every session and 447 once invoked, about $0.0000 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 2026-08-31.
always-on-guidance compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| always-on-guidanceunbound-force/gaze | Skill | 4 | yesterday | Apache-2.0 | A | 12 | OpenCode |
| codingoyi77/1ai-skills | Skill | 17 | yesterday | MIT | A | 54 | Claude Code |
| dev-loopswDomass/AI_orchestrator | Skill | 5 | 5d ago | MIT | A | 22 | Claude Code, Codex |
| Agent Evaluation Framework BuilderNotysoty/openagentskills | Skill | 9 | 2mo ago | MIT | A | 36 | Claude Code, Codex |
| Code Review ChecklistNotysoty/openagentskills | Skill | 9 | 2mo ago | MIT | A | 26 | Claude Code, Codex |
| code-reviewerhalexzd686-cloud/SoloFlow | Skill | 0 | 5d ago | MIT | A | 24 | Claude Code, Codex |
| code-reviewerlibrefang/librefang-registry | Skill | 11 | 1mo ago | MIT | A | 17 | Claude Code, Codex |