Skip to content
Back to skills

Tasks

ASecurity

skills/orchestrate/SKILL.md lists lens 6 `Excess` after lens 5, and all three tier statements in SKILL.md (profile table row, Phase 4 Lens set by tier paragraph) include lens 6 for every tier. - wiki/qa/document-verification/editing-a-gated-document.md — use for: anchor inventory before editing (lens_order, "exactly five", "1 and 3 only") - wiki/qa/process/fresh-context-code-review.md — use for: why the check sits in the fresh-context reviewer (D1) - the lens 6 text, verbatim, in plans/excess-

  • 5 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added October 6, 2026
ai-agentsgobashnodecode-review

Security analysis

A100/100

Pro scans all 20 files and shows the line behind each finding

Scanned October 6, 2026

npx -y skills add choiyounggi/dev-loop --skill tasks --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Tasks?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Tasks
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/choiyounggi-tasks/badge)](https://www.skillsdirectory.com/skills/choiyounggi-tasks)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
# Task 05: orchestrate Phase 4 gains lens 6 Excess at every tier
## Objective
skills/orchestrate/SKILL.md lists lens 6 `Excess` after lens 5, and all three tier statements in SKILL.md (profile table row, Phase 4 Lens set by tier paragraph) include lens 6 for every tier.
## Wiki pages (read these first, only these)
- wiki/qa/document-verification/editing-a-gated-document.md — use for: anchor inventory before editing (lens_order, "exactly five", "1 and 3 only")
- wiki/qa/process/fresh-context-code-review.md — use for: why the check sits in the fresh-context reviewer (D1)
## Inputs
- the lens 6 text, verbatim, in plans/excess-lens-and-lint-gate/lens6.txt
- Decisions that bind you: D1, D2, D3, D4
## Steps
1. Tests first.
   tests/orchestrate-review-pass.bats: (a) the order test becomes "Phase 4 contains the six lenses, numbered 1-6, in order", requires `lens_order` = `123456` and `Excess` in the section; (b) the test-quality-auditor test asserts `6. **Excess` present and `7. **` absent (comment: "the lens list is fixed at six"); (c) the strip negative control adds `Excess` to its grep -v alternation and compares to `123456`; the swap negative control compares to `123456`; (d) new test, whitespace-normalized (`tr '\n' ' ' | tr -s ' '`): Phase 4 contains `name the brief or plan line it serves`, `zero call sites outside its own tests`, `standard-library/language function`, `exactly one implementation`, `belongs to lens 1`, and `goes under Non-blocking`; (e) negative control for (d): a copy with every line from `6. **Excess` to the line containing `Non-blocking.` deleted fails (d); update the header comment's `four-lens` to `six-lens`.
   tests/orchestrate-dispatch-contracts.bats: line-384 assertion becomes `| review lenses | 1, 3 and 6 only | 1-4 and 6 | 1-6 | 1-6 plus the adversarial-change-review techniques recorded under lens 5 |`; the Phase 4 lens-set test asserts `lenses 1, 3 and 6 only`, `when R1, lenses 1-4 and 6`, `when R2 or R3, lenses 1-6`; add a negative control: a copy with `lenses 1-4 and 6` replaced by `lenses 1-4` fails the R1 assertion.
2. SKILL.md Phase 4: insert the lens6.txt block directly after the lens 5 line (`5. **AC traceability**...`), before the blank line preceding `**Lens set by tier.**`.
3. SKILL.md Phase 4 Lens set by tier paragraph: `it runs lenses 1 and 3 only` -> `it runs lenses 1, 3 and 6 only`; `when R1, lenses 1-4; when R2 or R3,` + `lenses 1-5.` -> `when R1, lenses 1-4 and 6; when R2 or R3,` + `lenses 1-6.` (reflow the paragraph's line breaks only as needed).
4. SKILL.md Phase 2 profile table row: `| review lenses | 1 and 3 only | 1-4 | 1-5 | 1-5 plus the adversarial-change-review techniques recorded under lens 5 |` -> `| review lenses | 1, 3 and 6 only | 1-4 and 6 | 1-6 | 1-6 plus the adversarial-change-review techniques recorded under lens 5 |`.
5. SKILL.md Phase 4: `continue to the four-lens pass unchanged` -> `continue to the lens pass unchanged`.
6. SKILL.md Preflight role list (plan repair from task 04c's sweep): `` `verify` (test/build/QA`` + newline + ``command)`` -> `` `verify` (test/build/lint/typecheck/QA`` + newline + ``command)``; test it in tests/orchestrate-dispatch-contracts.bats (whitespace-normalized): Preflight text contains `` `verify` (test/build/lint/typecheck/QA command)``.
## Deliverables
- skills/orchestrate/SKILL.md
- tests/orchestrate-review-pass.bats
- tests/orchestrate-dispatch-contracts.bats
## Verify
- PATH=/opt/homebrew/bin:$PATH bats tests/orchestrate-review-pass.bats tests/orchestrate-dispatch-contracts.bats tests/orchestrate-token-budget.bats tests/orchestrate-fresh-reviewer.bats — success = no `not ok` line
- lint: node scripts/wiki-lint-prohibitions.js wiki && echo LINT_OK — success = LINT_OK printed
- lint: bash scripts/gen-agent-tier-variants.sh --check && echo LINT_OK — success = LINT_OK printed
- covers: R1, R2
## Out of scope
- review-report.md (task 06); agents/task-reviewer*.md (task 07); integration-reviewer (not in this plan)

Files in this skill

  • 01-lint-surveyed-check.md3.2 KB
  • 02-gate-a-emits-lint-surveyed.md2.6 KB
  • 03-wiki-plan-lint-prose.md4.5 KB
  • 04-configure-verify-lint.md2.2 KB
  • 04b-verify-wording-readmes.md1.6 KB
  • 04c-verify-wording-loop-and-example.md1.8 KB
  • 04d-verify-wording-resolve-tools.md1.6 KB
  • 05-excess-lens-skill.md3.9 KB
  • 06-excess-lens-report-template.md1.9 KB
  • 07-excess-lens-agent.md2.3 KB
  • 08-lens6-seam-exemption.md1.6 KB
  • 09a-lint-none-needs-a-command.md1.1 KB
  • 09b-red-baseline-row-and-step0.md2 KB
  • 10-verify-wording-leftovers.md1.4 KB
  • 11a-plan-gate-crlf.md1.7 KB
  • 11b-emit-gaps-crlf.md1.1 KB
  • 12-red-baseline-empty-list.md2 KB
  • 13a-every-cr-dropped.md1.4 KB
  • 13b-lint-line-nounset-safe.md1.5 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.