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 pantheon-org/tekhne --skill plan-executegit clone --depth 1 https://github.com/pantheon-org/tekhneWrote 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/pantheon-org/tekhne/plan-execute)<a href="https://agentmods.dev/skills/pantheon-org/tekhne/plan-execute"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/plan-execute/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/pantheon-org/tekhne/plan-execute"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/plan-execute.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 | $0.00134 | $0.04014 |
| Opus 5 | $0.00067 | $0.02007 |
| Sonnet 5 | $0.00027 | $0.00803 |
| Haiku 4.5 | $0.00013 | $0.00401 |
Grade B, and why
plan-execute scanned grade B with 1 finding 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 9d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
- [ ] Did I re-run any command that failed until it passed? How it starts
The opening of the file, as written. The whole thing — 486 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Execute — Checklist-Driven Implementation with Honest Proof
Execute an implementation plan through its phases, validating every task with verifiable proof before marking it done. If proof is missing or falsified, the agent goes back and completes the work. No exceptions.
Core Principle
HONESTY IS NON-NEGOTIABLE. A checked item without proof is a lie. A plan with lies is not done. Broken trust means the implementation cannot be trusted and must be redone.
At a Glance
- Baseline — run all gates before touching code.
- Checklist — create
.context/plans/<slug>/CHECKLIST.mdwith every task. - Per-task — work, quick-gate after 1-3 file ops, full-gate at task end.
- Per-phase — all tasks done → phase gate suite → domain invariant → commit.
- Final — full gates + global audit + checklist integrity audit → DONE.
If any step fails: stop, fix, re-run, record proof. No exceptions.
Position in the Workflow
plan-create / implementation-planner → plan-review → plan-execute → commit / merge
(design) → (audit) → (implement) → (ship)
Prerequisites
- A
.context/plans/*.mdplan file with valid frontmatter, phases, and tasks - The plan has been reviewed (status: ACTIVE or DRAFT with explicit go-ahead)
opencode.jsonhassubAgentsconfigured for large-phase delegation- A working branch exists or can be created per the plan's branch workflow
Inputs
- Plan path —
.context/plans/<plan-slug>/README.md - Phase files —
.context/plans/<plan-slug>/phases/phase-*/README.md - Task files —
.context/plans/<plan-slug>/phases/phase-*/tasks/*.md - Branch name — from the plan or user
- Gate commands — from
AGENTS.md,package.json, or CI config
Outputs
- CHECKLIST.md — living checklist at
.context/plans/<plan-slug>/CHECKLIST.md - Commits — one per phase, with evidence in message body
- Execution Report — appended to the plan's
README.md - Updated plan frontmatter —
status: DONE(only when fully validated)
What ships with it
15 files 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.
- evals/instructions.json 4.5 KB
- evals/scenario-01/capability.txt 265 B
- evals/scenario-01/criteria.json 1.4 KB
- evals/scenario-01/task.md 2.5 KB
- evals/scenario-02/capability.txt 222 B
- evals/scenario-02/criteria.json 1.2 KB
- evals/scenario-02/task.md 2.3 KB
- evals/scenario-03/capability.txt 208 B
- evals/scenario-03/criteria.json 1.4 KB
- evals/scenario-03/task.md 2.6 KB
- evals/scenario-04/capability.txt 196 B
- evals/scenario-04/criteria.json 1.0 KB
- evals/scenario-04/task.md 1.9 KB
- evals/summary.json 313 B
- references/checklist-templates.md 3.0 KB
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.
- 9d ago First seen · 486 lines · 134 tokens per session scan B 20687ad1317e
plan-execute is a skill published in the GitHub repository pantheon-org/tekhne (10 stars, last pushed yesterday), licensed MIT. It adds 134 tokens to every session and 4,014 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
test-driven-development
Drives development with tests using the red-green-refactor loop. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.
skillshare-implement-feature
Implement a feature from a spec file or description using TDD workflow. Use this skill whenever the user asks to: add a new CLI command, implement a feature from a spec, build new functionality, add a flag, create a new internal package, or write Go code for skillshare. This skill enforces test-first development…
create-custom-grader
Use when converting an existing benchmark, rubric, verifier, task YAML/JSON, or domain check into SkillEvaluator BYOG/BYOT custom evaluation.
story-origin-check
Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.
prompt-proximity-architecture
Turn an approved measurement charter, ICPs, and buyer jobs into a budget-aware prompt coverage blueprint across proximity bands, aided status, information acts, journey states, roles, locales, evidence grades, partitions, and measurement lanes. Use before prompt wording to define required, optional, and prohibited…
xdto-validate
A validator for XDTO packages in 1C:Enterprise. It checks the package model, its metadata object, and its connection to the configuration.