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/seven128/project-tiny-context-harness/long-task-workflownpx skills add Seven128/project-tiny-context-harness --skill long-task-workflowgit clone --depth 1 https://github.com/Seven128/project-tiny-context-harnessWrote 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/seven128/project-tiny-context-harness/long-task-workflow)<a href="https://agentmods.dev/skills/seven128/project-tiny-context-harness/long-task-workflow"><img src="https://agentmods.dev/badge/skills/seven128/project-tiny-context-harness/long-task-workflow.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 | $0.00050 | $0.02927 |
| Opus 5 | $0.00025 | $0.01463 |
| Sonnet 5 | $0.00010 | $0.00585 |
| Haiku 4.5 | $0.00005 | $0.00293 |
Grade A, and why
long-task-workflow 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 3d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Single-Goal Long-Task Workflow
Boundaries
Use one currently selected host execution Goal, one repository, one selected verification workspace, one complete Contract and one Final Gate. This workflow never creates, invokes or manages a scheduler, agent runtime, App Server, branch/worktree fan-out, merge, push, PR, deployment, legacy orchestration chain, matrix, verdict or second Contract plan. The parent Goal owns Source, Contract, Authority, architecture, Context writeback, integration, current-candidate checks, formal verification, Final Gate, close and completion. Harness never allocates, schedules, retries or recovers delegated workers; their reports are not Progress, Evidence or proof, and every result must converge into the selected verification workspace before verification counts. Never activate from task size alone.
That Goal is host/user-selected; Harness does not create, persist or reconnect a Goal identifier. Compaction may continue inside it; a later physical Goal/session restores semantic state through resume, not a prior Turn. With a valid binding, run ty-context long-task resume <workdir>, then directly load the installed long-task-workflow Skill; recovery needs no implicit invocation.
The host/user owns model selection. Exactly one unconditional terminal-turn checkpoint follows the first Authority Lock before implementation. Harness neither switches nor verifies the model, persists checkpoint/acknowledgement/route state, nor creates a model scheduler, automatic switch or native-Goal completion state. Do not otherwise pause a healthy Goal solely to change models.
A Codex-root long-task install may expose fixed package-owned long_task_implementation with child agents disabled. It is static, stateless, non-Authority and post-checkpoint; install proves neither selection nor effective model/reasoning/tier. Profile and spawn never set service_tier. Exact-call or capability failure returns a packet to the parent; never infer it, use a generic child, or add tiers/retry/scheduling.
What ships with it
5 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.
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.
- 3d ago First seen · 76 lines · 50 tokens per session scan A fd6686eeda28
long-task-workflow is a skill published in the GitHub repository Seven128/project-tiny-context-harness (3 stars, last pushed 3d ago), licensed MIT. It adds 50 tokens to every session and 2,927 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
context-diet
Measure and compact an oversized agent-context file (CLAUDE.md, .cursorrules, AGENTS.md, a system prompt) without losing rules, or safely run reversible bounded, reversible ablation when intentional/aggressive context removal is requested. Triggers: "CLAUDE.md too big", "over the char limit", "context file too large"…
audit-onboarding-proposal
Independently audit a brownfield onboarding transcript, operational map, or exact proposed documentation patch before application. Use when a fresh reviewer must verify an $onboard-repository first pass, distinguish environment-caused Unknowns from reasoning defects, score its safety and evidence gates, or run a…
engineering-wisdom
Provide an explicitly requested, repository-grounded engineering review using contextual heuristics for code clarity, SOLID and design, testing, refactoring, architecture, and professional practice. Use only when the user invokes $engineering-wisdom or explicitly asks for this installed engineering-wisdom pack; do not…
red-team-adversarial
Adversarial security and resilience analysis — auto-triggered during /review and /test based on task classification. Provides attack surface analysis, boundary testing, auth bypass attempts, dependency chain attacks, and Beast Mode stress testing.
product-decision-agent
中文产品决策 Agent。用于中国大陆互联网产品、运营、增长、商业化、数据、项目推进和组织协作场景：产品规划、需求分析、PRD、需求优先级、排期、版本规划、Roadmap、MVP、灰度、上线、迭代、增长停滞、拉新、投放、渠道、裂变、CAC、LTV、ROI、留存、转化、DAU/MAU、GMV、漏斗、社区运营、内容供给、创作者、用户运营、活动运营、私域、会员、定价、指标异常、数据口径、埋点、A/B…
multi-agent-room
Orchestrate a team of named subagents in shared threads. One orchestrator drives multiple peers with distinct identities; each subagent sees its own inbox and can cross-check findings by posting to a thread the peer is a member of.