Tune
Necmttn/ax
Retrospective on one coding session that proposes changes to the agent's environment (hooks, checks, steering files, tool access) and files each as an ax proposal.
Run and interpret a read-only retrospective over Harness ledger projections, then prepare evidence-backed mechanism fixes, deletion candidates, or time-bounded rule proposals for human adjudication.
Install Harness Reckoning
$ npx skills add FairladyZ625/harness-anything --skill harness-reckoning -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install FairladyZ625/harness-anything harness-reckoning --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/FairladyZ625/harness-anything.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/harness-reckoning .claude/skills/harness-reckoning && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "harness-reckoning" agent skill from https://github.com/FairladyZ625/harness-anything/tree/main/skills/harness-reckoning into .claude/skills/harness-reckoning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-reckoning", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/FairladyZ625/harness-anything/tree/main/skills/harness-reckoningType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add FairladyZ625/harness-anything --skill harness-reckoning -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install FairladyZ625/harness-anything harness-reckoning --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/FairladyZ625/harness-anything.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/harness-reckoning .agents/skills/harness-reckoning && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "harness-reckoning" agent skill from https://github.com/FairladyZ625/harness-anything/tree/main/skills/harness-reckoning into .agents/skills/harness-reckoning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-reckoning", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add FairladyZ625/harness-anything --skill harness-reckoning -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install FairladyZ625/harness-anything harness-reckoning --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/FairladyZ625/harness-anything.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/harness-reckoning .cursor/skills/harness-reckoning && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "harness-reckoning" agent skill from https://github.com/FairladyZ625/harness-anything/tree/main/skills/harness-reckoning into .cursor/skills/harness-reckoning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-reckoning", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/FairladyZ625/harness-anything.git --path skills/harness-reckoning--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add FairladyZ625/harness-anything --skill harness-reckoning -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install FairladyZ625/harness-anything harness-reckoning --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/FairladyZ625/harness-anything.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/harness-reckoning .gemini/skills/harness-reckoning && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "harness-reckoning" agent skill from https://github.com/FairladyZ625/harness-anything/tree/main/skills/harness-reckoning into .gemini/skills/harness-reckoning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-reckoning", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install FairladyZ625/harness-anything harness-reckoningInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add FairladyZ625/harness-anything --skill harness-reckoning -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/FairladyZ625/harness-anything.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/harness-reckoning .github/skills/harness-reckoning && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "harness-reckoning" agent skill from https://github.com/FairladyZ625/harness-anything/tree/main/skills/harness-reckoning into .github/skills/harness-reckoning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-reckoning", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add FairladyZ625/harness-anything --skill harness-reckoning -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install FairladyZ625/harness-anything harness-reckoning --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/FairladyZ625/harness-anything.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/harness-reckoning .opencode/skills/harness-reckoning && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "harness-reckoning" agent skill from https://github.com/FairladyZ625/harness-anything/tree/main/skills/harness-reckoning into .opencode/skills/harness-reckoning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-reckoning", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
harness-reckoning- GitHub stars
- 226
- Token cost
- ~768 tokens
- SKILL.md length
- 411 words
- Files
- 4 (incl. references)
- Skills in repo
- 12
- Repo updated
- First seen
- Licence
- AGPL-3.0
At a glance
Run and interpret a read-only retrospective over Harness ledger projections, then prepare evidence-backed mechanism fixes, deletion candidates, or time-bounded rule proposals for human adjudication.
- Works in 4 steps: Fix the mechanism, configuration, or… → If no framework fix applies, propose… → Only then consider a new rule; require a… → …
- Tasks that involve Proposals and quotes
- SKILL.md covers Run, Adjudicate, Boundaries and Make it yours, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Harness Reckoning is an agent skill from FairladyZ625/harness-anything. Run and interpret a read-only retrospective over Harness ledger projections, then prepare evidence-backed mechanism fixes, deletion candidates, or time-bounded rule proposals for human adjudication.
Its SKILL.md is about 770 tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `agents/openai.yaml`, `references/method.md` and `references/source-contract.md`).
It sits in Product & Project Management, covering Proposals and quotes and Retrospectives. The repository describes itself as: Clean-room Harness rewrite monorepo. The licence is AGPL-3.0.
When your agent uses it
- Tasks that involve Proposals and quotes
- Tasks that involve Retrospectives
Example prompts
- “/harness-reckoning”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Fix the mechanism, configuration, or error message that created the friction.
- If no framework fix applies, propose removal of an obsolete rule.
- Only then consider a new rule; require a trigger and expiration date.
- A second occurrence of the same class is a structural problem, not permission for another local patch.
What it can do on your machine
Read from SKILL.md and the folder at commit c805ddf. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Harness Reckoning loads about 768 tokens when it runs, and up to ~1.2k if it reads all its reference files. Until then it costs about 54 tokens; SKILL.md has 411 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from FairladyZ625/harness-anything at commit c805ddf, republished under its AGPL-3.0 licence (© FairladyZ625). 411 words, ~768 tokens.
Download SKILL.mdSave it as
.claude/skills/harness-reckoning/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- harness-reckoning
- description
- Run and interpret a read-only retrospective over Harness ledger projections, then prepare evidence-backed mechanism fixes, deletion candidates, or time-bounded rule proposals for human adjudication.
Harness Reckoning
Use this skill for a periodic, offline review of repeated friction without allowing the reviewer to modify rules, Tasks, Facts, or Decisions.
Run
The system preset starts paused because a new Harness may not have an agent runtime. Choose an agent and runtime instance, then enable it. Its mission invokes:
ha schedule reckonThe command reads the attached Harness projection and writes only stdout. The occurrence runtime's final output is the report artifact. A missing projection is an error, never a healthy empty report. Open candidate evidence with the relevant read commands, such as ha task show, ha runtime status, and ha fact show. Do not run commands that record or change entities.
Optional sources follow references/source-contract.md. Add their read command and evidence-merging instructions to the preset mission.
Adjudicate
Read the evidence link or identifier on every candidate. Apply the funnel in order:
- Fix the mechanism, configuration, or error message that created the friction.
- If no framework fix applies, propose removal of an obsolete rule.
- Only then consider a new rule; require a trigger and expiration date.
- A second occurrence of the same class is a structural problem, not permission for another local patch.
The report is advisory. A human decides whether to create a Task, retire a rule, or propose a Decision. Quiet output is a valid health attestation; never manufacture findings.
Show full SKILL.md (185 more words)Show less
Boundaries
Occurrence claim ownership (nodeId plus claimFence) supplies multi-node mutual exclusion. Each result belongs to its occurrence; no shared report path is used. Edge nodes read their local projection, so the report identifies local evidence rather than pretending to be a fleet-wide canonical snapshot.
Make it yours
- Edit the preset mission to change the questions, evidence depth, or report format.
- Add a read-only external source and tell the mission how its evidence joins the built-in signals.
- Select or replace the agent and runtime instance in the Schedule editor. The preset remains protected from deletion, but its cadence, timezone, mission, and target are yours to change.
External source examples
A software team may add a walls report or inspect an AGENTS.md retirement marker. Another team might read support escalations, operations handoffs, or a customer feedback export. These are site-specific inputs and are never part of the built-in signal set. A source must declare its read scope and return stable evidence identifiers.
The method uses offline replay, external evidence, a minimal proposed difference, and human adjudication. It deliberately avoids online self-editing and append-only memory growth. See references/method.md.
© FairladyZ625, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 3 other files (references) in skills/harness-reckoning of FairladyZ625/harness-anything.
- SKILL.md
- agents/openai.yaml
- references/method.md
- references/source-contract.md
Open the folder on GitHubat commit c805ddf
Compare with similar skills
Harness Reckoning next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Harness Reckoning this skillFairladyZ625/harness-anything | 226 | — | ~768 | Automated safety check: Pass | AGPL-3.0 | |
| TuneNecmttn/ax | 115 | — | ~1.3k | Automated safety check: Pass | AGPL-3.0 | |
| RetroNecmttn/ax | 115 | — | ~3.5k | Automated safety check: Pass | AGPL-3.0 | |
| Self Retrospectivekid0317/crewai_mas_demo | 165 | — | ~505 | Automated safety check: Pass | None | |
| Weekly Engineering Retrogarrytan/gstack | 136k | — | ~2.4k | Automated safety check: Pass | MIT | |
| Dough Execute Planterryyin/lizard | 2.5k | — | ~4.3k | Automated safety check: Pass | Custom licence |
Similar skills
Retro
Necmttn/ax
Guided experiment-loop retrospective over the ax agent-experience graph.
Self Retrospective
kid0317/crewai_mas_demo
Agent 自我复盘：读取 L2/L3/L1 日志，调用 LLM 生成结构化改进提案， 写入 proposals.json 并发通知至 human.json 等待审批。
Weekly Engineering Retro
garrytan/gstack
Builds a weekly engineering retrospective from git history: commit counts, per-person contributions, work patterns and code quality numbers over a chosen window.
Dough Execute Plan
terryyin/lizard
Executes one selected story or bounded retrospective correction through an executable plan, or one authorized planless slice from a selected simple story or a contextual instruction, with…
Oral Paper Skill
Adkid-Zephyr/oral-paper-skill
Help authors learn from exemplary ICLR, ICML, and NeurIPS papers through source-linked manuscript comparisons, concrete writing and experiment suggestions, and guided reflection.
More from FairladyZ625/harness-anything
All 12 skills in this repoHarness Contributing
FairladyZ625/harness-anything
Contribute a public change to Harness Anything from a GitHub issue through an isolated worktree, scoped tests, manifest-selected gates, a complete bilingual PR body, review triage, and maintainer…
Gate Customization
FairladyZ625/harness-anything
在目标仓库 harness.yaml 的 settings.gates 里声明与定制任务完成门：local-command 本地命令见证、manual-attest 人工签字、github-actions CI 见证、none 显式免除，治理字段 mandatorySignoff（双控签注）与 allowOverride（owner 特批），以及…
Preset Creator
FairladyZ625/harness-anything
Create, review, or update Harness Anything preset-manifest/v3 packages, including profiles, completion gates, template selections, output shapes, script entrypoints, capability declarations, package…
Preset Trigger
FairladyZ625/harness-anything
Start Harness Anything task creation by choosing a software/coding preset first.
Task Explainer HTML
FairladyZ625/harness-anything
产出与增量维护任务包中的活解释页 artifacts/explainer.html；按物化模板中的唯一权威注释编写，并消费派工注入的 task-context 因果上下文。Use when a task-bound dispatch requires creating, updating, or freezing the task's living explainer page, or…
Vertical Creator
FairladyZ625/harness-anything
Create, review, or update Harness Anything verticals. An agent skill from FairladyZ625/harness-anything.
Related
Categories
Questions about Harness Reckoning
What does Harness Reckoning do?
Run and interpret a read-only retrospective over Harness ledger projections, then prepare evidence-backed mechanism fixes, deletion candidates, or time-bounded rule proposals for human adjudication. Harness Reckoning is an agent skill from FairladyZ625/harness-anything. Run and interpret a read-only retrospective over Harness ledger projections, then prepare evidence-backed mechanism fixes, deletion candidates, or time-bounded rule proposals for human adjudication.
When should I use Harness Reckoning?
Harness Reckoning fits situations like: tasks that involve Proposals and quotes; tasks that involve Retrospectives.
How do I install Harness Reckoning in Claude Code?
Run `npx skills add FairladyZ625/harness-anything --skill harness-reckoning -a claude-code`. Or copy the skill folder (skills/harness-reckoning in FairladyZ625/harness-anything) into .claude/skills/harness-reckoning in your project. Claude Code loads it when a task matches its description.
How do I install Harness Reckoning in Codex?
Run `npx skills add FairladyZ625/harness-anything --skill harness-reckoning -a codex`. Or copy the skill folder (skills/harness-reckoning in FairladyZ625/harness-anything) into .agents/skills/harness-reckoning in your project. Codex loads it when a task matches its description.
Can I use Harness Reckoning in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add FairladyZ625/harness-anything --skill harness-reckoning -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/harness-reckoning, .gemini/skills/harness-reckoning, .github/skills/harness-reckoning and .opencode/skills/harness-reckoning in your project.
What does Harness Reckoning need to run?
SKILL.md names no scripts, command-line tools or credentials: Harness Reckoning is instructions for the agent only.
Does Harness Reckoning access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Harness Reckoning safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Harness Reckoning use?
Harness Reckoning is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Harness Reckoning use?
About 768 tokens (SKILL.md is roughly 3.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 454 tokens, read only when the agent opens those files.
What are the alternatives to Harness Reckoning?
Skills that share tags, products or a category with Harness Reckoning: Tune (Necmttn/ax, 115 stars), Retro (Necmttn/ax, 115 stars), Self Retrospective (kid0317/crewai_mas_demo, 165 stars) and Weekly Engineering Retro (garrytan/gstack, 136k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Harness Reckoning?
FairladyZ625 (a GitHub user) maintains it in FairladyZ625/harness-anything, which has 226 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 10, 2026.
Source: FairladyZ625/harness-anything on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.