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 jeffreytse/grimoire-core --skill apply-commit-with-no-retreatgit clone --depth 1 https://github.com/jeffreytse/grimoire-coreWrote 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/jeffreytse/grimoire-core/apply-commit-with-no-retreat)<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-commit-with-no-retreat"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-commit-with-no-retreat/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/jeffreytse/grimoire-core/apply-commit-with-no-retreat"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-commit-with-no-retreat.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 | $0.00062 | $0.03714 |
| Opus 5.5 | $0.00025 | $0.01486 |
| Sonnet 5.5 | $0.00012 | $0.00743 |
| Haiku 4.5 | $0.00006 | $0.00371 |
Grade A, and why
apply-commit-with-no-retreat 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 4d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply Commit with No Retreat
Identify where hedging is degrading performance — the preserved exit that makes full commitment feel unnecessary — then deliberately destroy that exit before the operation begins, so that the only path remaining is forward; because the performance gap between a team that cannot retreat and a team that can is not motivational but structural: the brain allocates differently when escape is genuinely impossible.
Why This Is Best Practice
Origin: In 205 BC, Han Xin (韩信), general of Liu Bang's Han army, led approximately 10,000 soldiers against the Zhao state's force of 200,000 at the Battle of Jingxing (井陉之战). In the night before battle, Han Xin positioned his main force with their backs to the Zhang River — a formation his officers immediately recognised as contrary to every principle of military doctrine. Classical doctrine stated: "occupy high ground on the right and behind; keep water and marshes on the left and in front." Placing troops with water behind them eliminated the retreat option entirely. When battle began, the Han soldiers — unable to fall back into the river — fought with a ferocity that reversed the numerical disadvantage. The Zhao army, pursuing what appeared to be an easy rout, was caught between Han Xin's main force (fighting with desperate intensity) and a flanking force of 2,000 cavalry Han Xin had pre-positioned. Zhao was destroyed. Afterwards, Han Xin's officers demanded an explanation: he replied: "Put them in a position where there is no way out, and they will fight to the death." (置之死地而後生 — "Place them in a deadly ground and they will survive.") The phrase 背水一战 (back to the water, one battle) became the canonical expression of commitment-through-irreversibility.
Adopted by: The mechanism is not unique to military history. Hernán Cortés, landing in Mexico in 1519 with 600 men facing the Aztec empire, ordered his eleven ships burned and scuttled after establishing the beachhead — removing the option for his soldiers to retreat to Cuba. The soldiers could not return; they could only conquer or die. The psychological effect was identical to Han Xin's river: the brain stops modelling the exit scenario and allocates fully to the forward path. Robert Cialdini documented the same mechanism in Influence (1984): commitments that are public, active, and irrevocable produce the strongest subsequent performance because cognitive consistency requires the person to support what they can no longer reverse. Dan Ariely's work on commitment devices (Predictably Irrational, 2008) formalised the principle in behavioural economics: humans systematically underperform when they preserve optionality, because optionality enables the hedging decision in each micro-moment of effort.
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.
- 4d ago Changed · +1 lines 186de447e8fb
- 1mo ago First seen · 127 lines · 62 tokens per session scan A df5e928fa9fa
apply-commit-with-no-retreat is a skill published in the GitHub repository jeffreytse/grimoire-core (5 stars, last pushed 5d ago), licensed MIT. It adds 62 tokens to every session and 3,714 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
org-report
Generate an executive organization brief (leadership chain, direct reports, extended teams, and vendor partners) for a target person. Produces a Word + PDF report from a directory MCP source (WorkIQ is the reference implementation) and displays it in a Copilot canvas. Triggers on "generate org report for X", "build…
coaching-techniques
GROW model, active listening, developmental feedback, and team growth approaches.
meeting-efficiency
Agenda design, time boxing, decision capture, async alternatives, and productive facilitation.
stakeholder-management
Influence mapping, communication strategies, and expectation management for complex organizations.
scaffolding-generator
Pattern-aware code scaffolding that detects existing conventions and generates new components matching the codebase style. Use when asked to "scaffold a component", "generate boilerplate", "create a new module", "bootstrap a service", "add a new endpoint", "create a new controller", or "add a new feature module".…
status-reporting
Create stakeholder-friendly project status updates and progress reports.