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: standards3description: Load only the standards relevant to a4---5
6# Standards — focused engineering guidance
7
8Load the smallest set of standards justified by the caller's files, language,
9and risks. Do not preload the entire reference corpus.
10
11## Procedure
12
131. Record the supplied paths, language, change type, and risk cues.
142. Load `common-standards.md` plus only the matching language or checklist
15 references.
163. Compare the supplied artifact to those sources.
174. Return cited findings with path and line when possible, plus checked and
18 not-checked scope.
195. Stop.
20
21This skill provides context and findings. It does not edit, validate, retry,
22approve, commit, release, deliver, or decide continuation.
23
24## Mutation-safety standards
25
26When the supplied change rewrites existing files in bulk — formatters,
27codemods, migration scripts, generators pointed at hand-written sources —
28check it against three standards and report each as a finding when absent:
29
30- **Single audited mutation chokepoint.** All rewrites flow through one named
31 command or script whose inputs, outputs, and dry-run mode can be inspected.
32 Edits scattered across ad-hoc one-liners and manual touch-ups are the
33 **diffuse mutation** failure mode: no single point can be audited, re-run,
34 or blamed. Finding: name every mutation path outside the chokepoint.
35- **Hash-witnessed backups before rewrite.** Before the chokepoint runs, the
36 originals are preserved with content hashes recorded (a committed baseline
37 counts), so "the rewrite changed only what it claims" is checkable
38 byte-for-byte, not asserted. Finding: a bulk rewrite with no verifiable
39 before-state.
40- **Self-administered ambition gate.** The change states what it deliberately
41 does not touch, and the diff respects it. A formatter run that also renames,
42 a codemod that also refactors, is the **scope-creep rewrite** failure mode.
43 Finding: any file class in the diff outside the change's own stated scope.
44
45Stop condition for this check: all three standards have an explicit pass or
46finding; a bulk-rewrite review that reports style nits but skips these is
47incomplete.
48
49## References
50
51- [Common standards](references/common-standards.md)
52- [Go](references/go.md)
53- [Python](references/python.md)
54- [Rust](references/rust.md)
55- [TypeScript](references/typescript.md)
56- [JavaScript](references/javascript.md)
57- [Shell](references/shell.md)
58- [JSON](references/json.md)
59- [YAML](references/yaml.md)
60- [Markdown](references/markdown.md)
61- [SQL safety](references/sql-safety-checklist.md)
62- [Race conditions](references/race-condition-checklist.md)
63- [LLM trust boundaries](references/llm-trust-boundary-checklist.md)
64- [Skill structure](references/skill-structure.md)
65- [Test strategy](references/test-pyramid.md)
66
67---
68
69**Source:** [`hashgraph-online/awesome-codex-plugins`](https://github.com/hashgraph-online/awesome-codex-plugins) → `plugins/boshu2/agentops/skills-codex/standards/SKILL.md`
hashgraph-online