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 agentmods add skills/bostonaholic/team/implementing-slicesnpx skills add bostonaholic/team --skill implementing-slicesgit clone --depth 1 https://github.com/bostonaholic/teamWrote 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/bostonaholic/team/implementing-slices)<a href="https://agentmods.dev/skills/bostonaholic/team/implementing-slices"><img src="https://agentmods.dev/badge/skills/bostonaholic/team/implementing-slices.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.00734 |
| Opus 5 | $0.00014 | $0.00367 |
| Sonnet 5 | $0.00006 | $0.00147 |
| Haiku 4.5 | $0.00003 | $0.00073 |
Grade A, and why
implementing-slices 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementing Slices
Consume docs/plans/<id>/, implement one vertical slice at a time, and commit each atomically when its tests pass.
Dispatch modes
Initial dispatch (after the test-architect's failing tests are confirmed)
Read 8-plan.md (steps/tests), 7-structure.md (order/checkpoints), immutable failing acceptance tests, and 4-repos.md when present. In multi-repo mode, use each slug, absolute path, and ## Worktrees path; execute every [repo: <slug>] step and prefixed test inside that worktree. Run the suite once in every involved worktree to confirm the failing baseline.
Review-fix dispatch (after a hard-gate failure)
The orchestrator supplies a typed failure class and reviewer findings. Fix every named item:
- Security: fix the vulnerability directly—parameterize queries, remove secrets, add auth, escape output; never weaken the fix.
- Tests: change code, never the immutable tests. Code review: fix every
issue:. Lint/format/typecheck/build: rerun until passing; use--fixfirst where available. - For a non-obvious failure whose first fix is a guess, call the Skill tool with
systematic-debuggingand complete Root Cause Analysis (5 Whys) (principle-fix-root-causes). Skip it for an obvious typo, named assertion, or one-line correction.
Then run the full suite, resolve every failure type from the round, and report each fix. The orchestrator re-dispatches ALL 5 reviewers.
Slice-by-slice execution
- Follow plan order.
[sequential]steps depend on prior steps;[parallel]steps may reorder. Switch repo worktrees for[repo: <slug>]steps and<repo>:tests. - A slice finishes only when its acceptance tests and all prior-slice tests pass.
- Call the Skill tool with
git-commit: Conventional Commits, 50/72, one logical change. Single repo: one commit using the sliceCommit:subject and citing design/structure paths. Multi-repo slice: one commit per named repo using itsCommit:subject; each body cites the same paths and sayspart of slice <N>: <name>. - Report
{slice: <name>, testsPassing: [list], commits: [{repo: <slug>, sha: <sha>}, ...]}; single-repo has one commit entry. After all slices, return paths, slice list, and final test status.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today Changed · -80 lines · -33 tokens per session b462c4c783d9
- 2d ago Changed · +1 lines 47e9eb472fc4
- 5d ago First seen · 124 lines · 61 tokens per session scan A 50f621ac1b41
implementing-slices is a skill published in the GitHub repository bostonaholic/team (11 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 734 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other skills, from other repositories
behavior-contract
Bug condition/postcondition formalization as testable Behavior Contracts. Defines invariants that must be preserved across fixes.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
test-driven-development
Strict RED-GREEN-REFACTOR cycle enforcement. Tests are never skipped or deferred. Run mode only, never watch mode. Exit code evidence mandatory.
tdd-enforcement
Red-Green-Refactor TDD methodology with mandatory failing tests, minimal implementation, quality refactoring, and 80% coverage gating.
orchestrated-execution
Execute work units through the rigorous 4-phase Metaswarm cycle (Implement -> Validate -> Adversarial Review -> Commit) with independent quality gate enforcement.
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code. Creates bite-sized TDD implementation plans with dependency tracking.