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 skills add jamestexas/agents --skill implementgit clone --depth 1 https://github.com/jamestexas/agentsWrote 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/jamestexas/agents/implement)<a href="https://agentmods.dev/skills/jamestexas/agents/implement"><img src="https://agentmods.dev/badge/skills/jamestexas/agents/implement/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/jamestexas/agents/implement"><img src="https://agentmods.dev/badge/skills/jamestexas/agents/implement.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 | $0.00114 | $0.02202 |
| Opus 5.5 | $0.00046 | $0.00881 |
| Sonnet 5.5 | $0.00023 | $0.00440 |
| Haiku 4.5 | $0.00011 | $0.00220 |
Grade A, and why
implement 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
implement — implementation orchestrator
A fixed-sequence chain for implementing one unit of work (a feature or a fix) with the same determinism structural-pr-review brings to the review side. Ad-hoc implementation anchors on whatever the author noticed first; this chain guarantees the same evidence shape every time: decompose (P0) → research (P1) → TDD loop (P2) → self-review gate (P3) → structural review (P4) → close (P5).
Two non-negotiables:
- The human does the human-facing actions. This skill STOPS before
git push, before opening a PR, before posting any review/reply. It prepares and verifies; the human pushes and posts. (gitsign keyless enforces this — the final signature is the author's.) - Rigid gates emit artifacts. P0 and P3 do not "complete" until their required artifact exists. A phase cannot start until the prior gate's artifact is present. Everything else is FLEXIBLE within bounded exit conditions.
Arguments
$ARGUMENTS — a problem statement, a ticket ID, or a filed bead id. If empty, ask for one before proceeding.
Determinism contract
- Phases run in order P0→P5. No reordering.
- Each phase names the EXACT skill/command it invokes. No "use appropriate tooling."
- RIGID phases (P0, P3) produce a gating artifact named below; the next phase asserts it exists.
- FLEXIBLE phases (P1, P2) iterate, but each has an explicit EXIT CONDITION — not a fixed step count.
- Create one TodoWrite item per phase at the start; a phase is not checked off until its gate/exit condition is met.
P0 — SCOPE → bead specs (RIGID · gate: filed beads exist)
Decompose the work into dispatchable units and FILE them, closing the bead→implement bridge that the decomposition skills stop short of.
- If the input is an aspiration/capability → invoke
problem-decomposer. If it is a ticket/feature to cut into PR-sized units → invokework-scope. (Both emit specs and deliberately DO NOT file.) - File each emitted leaf/unit with
rsry_bead_create— carry its file scope + a falsifiable acceptance criterion (a runnable command or a named test). Link withrsry_bead_linkwhere dependent. - Checkpoint commit (jj/git) so the decomposition is durable before code starts.
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.
- 1mo ago Changed · +9 lines · -5 tokens per session cd20c5c83e0c
- 1mo ago First seen · 106 lines · 119 tokens per session scan A ee6cb02e1345
implement is a skill published in the GitHub repository jamestexas/agents (2 stars, last pushed 23d ago), licensed Apache-2.0. It adds 114 tokens to every session and 2,202 once invoked, about $0.0005 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 2026-09-11.
Other skills, from other repositories
tdd
Guidance for test-driven development (TDD), a method where you write a failing test, make it pass with a small change, and then improve the code. It focuses on tests that check user-visible behavior through public interfaces.
pair-programming
AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with…
web-dev-standards
Use when designing software architectures ('codebase-design' Deep Modules/Design-It-Twice), writing tests ('test-driven-development' mock boundaries), creating setup scripts ('interactive-wizard'), applying TypeScript, Next.js, Expo, or monorepo standards, or configuring shared-domain Resend email…
hotfix
Fixes an observed defect with reproducible evidence in one call: writes a short trace doc before touching code, implements the fix, and backs it with a regression test written before the fix. Production incidents are the motivating case, not a gate. When blocked, it halts by name and saves the doc for a later call to…
lfe-tdd
Red-green-refactor quality pass on code the Builder just wrote. Use in the Builder sub-pipeline after lfe-builder completes implementation.
Bug Fixing
Skill "Bug Fixing" from OpenLabor/openlabor, covering bug fixing, objective, process and guidelines.