Standards — focused engineering guidance
Load the smallest set of standards justified by the caller's files, language,
and risks. Do not preload the entire reference corpus.
Procedure
- Record the supplied paths, language, change type, and risk cues.
- Load
common-standards.md plus only the matching language or checklist
references.
- Compare the supplied artifact to those sources.
- Return cited findings with path and line when possible, plus checked and
not-checked scope.
- Stop.
This skill provides context and findings. It does not edit, validate, retry,
approve, commit, release, deliver, or decide continuation.
Mutation-safety standards
When the supplied change rewrites existing files in bulk — formatters,
codemods, migration scripts, generators pointed at hand-written sources —
check it against three standards and report each as a finding when absent:
- Single audited mutation chokepoint. All rewrites flow through one named
command or script whose inputs, outputs, and dry-run mode can be inspected.
Edits scattered across ad-hoc one-liners and manual touch-ups are the
diffuse mutation failure mode: no single point can be audited, re-run,
or blamed. Finding: name every mutation path outside the chokepoint.
- Hash-witnessed backups before rewrite. Before the chokepoint runs, the
originals are preserved with content hashes recorded (a committed baseline
counts), so "the rewrite changed only what it claims" is checkable
byte-for-byte, not asserted. Finding: a bulk rewrite with no verifiable
before-state.
- Self-administered ambition gate. The change states what it deliberately
does not touch, and the diff respects it. A formatter run that also renames,
a codemod that also refactors, is the scope-creep rewrite failure mode.
Finding: any file class in the diff outside the change's own stated scope.
Stop condition for this check: all three standards have an explicit pass or
finding; a bulk-rewrite review that reports style nits but skips these is
incomplete.
References
- Common standards
- Go
- Python
- Rust
- TypeScript
- JavaScript
- Shell
- JSON
- YAML
- Markdown
- SQL safety
- Race conditions
- LLM trust boundaries
- Skill structure
- Test strategy
Source: hashgraph-online/awesome-codex-plugins → plugins/boshu2/agentops/skills-codex/standards/SKILL.md
1---
2name: standards
3description: "Load only the standards relevant to a"
4category: ai-agents-and-harness
5source_repo: hashgraph-online/awesome-codex-plugins
6source_path: "plugins/boshu2/agentops/skills-codex/standards/SKILL.md"
7source_url: https://github.com/hashgraph-online/awesome-codex-plugins/blob/HEAD/plugins/boshu2/agentops/skills-codex/standards/SKILL.md
8metadata:
9 source: https://skillmd.com/skills/hashgraph-online/standards
10---
11
12# Standards — focused engineering guidance
13
14Load the smallest set of standards justified by the caller's files, language,
15and risks. Do not preload the entire reference corpus.
16
17## Procedure
18
191. Record the supplied paths, language, change type, and risk cues.
202. Load `common-standards.md` plus only the matching language or checklist
21 references.
223. Compare the supplied artifact to those sources.
234. Return cited findings with path and line when possible, plus checked and
24 not-checked scope.
255. Stop.
26
27This skill provides context and findings. It does not edit, validate, retry,
28approve, commit, release, deliver, or decide continuation.
29
30## Mutation-safety standards
31
32When the supplied change rewrites existing files in bulk — formatters,
33codemods, migration scripts, generators pointed at hand-written sources —
34check it against three standards and report each as a finding when absent:
35
36- **Single audited mutation chokepoint.** All rewrites flow through one named
37 command or script whose inputs, outputs, and dry-run mode can be inspected.
38 Edits scattered across ad-hoc one-liners and manual touch-ups are the
39 **diffuse mutation** failure mode: no single point can be audited, re-run,
40 or blamed. Finding: name every mutation path outside the chokepoint.
41- **Hash-witnessed backups before rewrite.** Before the chokepoint runs, the
42 originals are preserved with content hashes recorded (a committed baseline
43 counts), so "the rewrite changed only what it claims" is checkable
44 byte-for-byte, not asserted. Finding: a bulk rewrite with no verifiable
45 before-state.
46- **Self-administered ambition gate.** The change states what it deliberately
47 does not touch, and the diff respects it. A formatter run that also renames,
48 a codemod that also refactors, is the **scope-creep rewrite** failure mode.
49 Finding: any file class in the diff outside the change's own stated scope.
50
51Stop condition for this check: all three standards have an explicit pass or
52finding; a bulk-rewrite review that reports style nits but skips these is
53incomplete.
54
55## References
56
57- [Common standards](references/common-standards.md)
58- [Go](references/go.md)
59- [Python](references/python.md)
60- [Rust](references/rust.md)
61- [TypeScript](references/typescript.md)
62- [JavaScript](references/javascript.md)
63- [Shell](references/shell.md)
64- [JSON](references/json.md)
65- [YAML](references/yaml.md)
66- [Markdown](references/markdown.md)
67- [SQL safety](references/sql-safety-checklist.md)
68- [Race conditions](references/race-condition-checklist.md)
69- [LLM trust boundaries](references/llm-trust-boundary-checklist.md)
70- [Skill structure](references/skill-structure.md)
71- [Test strategy](references/test-pyramid.md)
72
73---
74
75**Source:** [`hashgraph-online/awesome-codex-plugins`](https://github.com/hashgraph-online/awesome-codex-plugins) → `plugins/boshu2/agentops/skills-codex/standards/SKILL.md`